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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11653
    Prev
    Next
    INDEX
    Explanations

    phrases indicating assessment or observation

    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
    373
    +0.15
    0.7%
    195
    +0.10
    0.5%
    683
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.15
    0.03
    544
    +0.10
    0.03
    183
    +0.10
    0.03
    Negative Logits
    ests
    -0.87
    orem
    -0.84
    otos
    -0.80
    ilts
    -0.75
    rouse
    -0.74
    andise
    -0.72
    rongh
    -0.70
    umbn
    -0.70
    atching
    -0.70
    izons
    -0.69
    POSITIVE LOGITS
     doubtful
    0.87
     unlikely
    0.82
     probable
    0.78
     odd
    0.76
     unclear
    0.74
     ironic
    0.73
     prudent
    0.72
     plausible
    0.71
     strange
    0.71
     feasible
    0.71
    Activations Density 0.050%

    No Known Activations