© 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. 8590
    Prev
    Next
    INDEX
    Explanations

    tips related to giving presentations and communication skills

    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
    480
    +0.18
    0.9%
    459
    +0.12
    0.6%
    373
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.18
    0.06
    351
    +0.12
    0.03
    119
    +0.11
    0.04
    Negative Logits
    ocaust
    -0.83
    death
    -0.73
    osate
    -0.73
    ageddon
    -0.71
     Armageddon
    -0.70
    illegal
    -0.69
    AIDS
    -0.69
    Death
    -0.69
    ocide
    -0.69
    Bomb
    -0.68
    POSITIVE LOGITS
     learners
    1.07
     contextual
    0.96
     understanding
    0.96
     insights
    0.95
     lear
    0.95
     learning
    0.93
     thoughtful
    0.93
     brainstorm
    0.92
     empath
    0.90
     helpful
    0.90
    Activations Density 1.080%

    No Known Activations