© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 10049
    Prev
    Next
    INDEX
    Explanations

    information about social issues and conflicts, particularly related to cyberbullying, animal welfare, bisexual misconceptions, Palestinian movement restrictions, and humanitarian assistance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.19
    0.9%
    600
    +0.10
    0.4%
    391
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.08
    67
    +0.10
    0.06
    600
    +0.09
    0.05
    Negative Logits
    ortium
    -0.77
    xon
    -0.73
    nw
    -0.73
    mble
    -0.68
    hp
    -0.66
    wered
    -0.64
    hiro
    -0.64
    Motor
    -0.64
    uristic
    -0.64
    swer
    -0.63
    POSITIVE LOGITS
     activities
    0.98
     interventions
    0.95
     activity
    0.93
     emergencies
    0.92
     engagements
    0.88
     affairs
    0.88
     outcomes
    0.87
     causation
    0.86
     entities
    0.85
     stimuli
    0.85
    Activations Density 0.374%

    No Known Activations