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 49152
    5. 8-RES_FS49152-JB
    6. 26262
    Prev
    Next
    INDEX
    Explanations

    terms related to physiological conditions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    461
    +0.12
    0.6%
    41
    +0.10
    0.4%
    85
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.01
    17
    +0.10
    0.01
    659
    +0.09
    0.01
    Negative Logits
    ible
    -0.81
    ipeg
    -0.80
    izen
    -0.80
    itarian
    -0.74
    ifiable
    -0.73
    ifier
    -0.70
     Leilan
    -0.69
    ariat
    -0.66
     Guilty
    -0.66
    ices
    -0.64
    POSITIVE LOGITS
    lla
    0.98
    lli
    0.91
    lly
    0.88
    tes
    0.88
    nces
    0.84
    nce
    0.83
    tic
    0.83
    xual
    0.82
    ll
    0.82
    ttes
    0.82
    Activations Density 0.011%

    No Known Activations