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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2686
    Prev
    Next
    INDEX
    Explanations

    mentions of people in public figures or influencers

    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
    36
    +0.24
    1.1%
    640
    +0.13
    0.6%
    393
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.24
    0.11
    250
    +0.13
    0.04
    646
    +0.11
    0.05
    Negative Logits
    lords
    -0.83
    cells
    -0.74
    effects
    -0.72
    anism
    -0.71
    abiding
    -0.70
     holders
    -0.68
    holders
    -0.68
     mills
    -0.66
    enance
    -0.65
    grounds
    -0.65
    POSITIVE LOGITS
     scathing
    1.23
     lengthy
    1.14
     brief
    1.05
     heartfelt
    1.05
     statement
    1.01
     bombshell
    1.00
     detailed
    0.98
     blister
    0.98
     keynote
    0.98
     whopping
    0.98
    Activations Density 0.201%

    No Known Activations