Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 837
    Prev
    Next
    INDEX
    Explanations

    dialogue in a fictional conversation

    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
    640
    +0.20
    0.9%
    481
    +0.16
    0.7%
    373
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.20
    0.08
    6
    +0.16
    0.08
    107
    +0.14
    0.05
    Negative Logits
    etheless
    -0.77
     migration
    -0.75
     regener
    -0.72
     synerg
    -0.71
     enriched
    -0.70
     travelling
    -0.69
     extrad
    -0.68
     inheritance
    -0.68
     vaccinations
    -0.66
     additive
    -0.66
    POSITIVE LOGITS
    Suddenly
    1.18
    Pause
    1.18
    Then
    1.15
    Sounds
    1.12
    Again
    1.10
    Well
    1.07
    Everyone
    1.04
    Fuck
    1.03
    Answer
    1.02
    Okay
    1.02
    Activations Density 0.221%

    No Known Activations