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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 40056
    Prev
    Next
    INDEX
    Explanations

    forms of the verb 'will,' indicating future actions or intentions

    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
    721
    +0.13
    0.6%
    451
    +0.12
    0.5%
    183
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.13
    0.02
    451
    +0.12
    0.02
    579
    +0.11
    0.02
    Negative Logits
    design
    -0.85
    cffffcc
    -0.73
    emark
    -0.71
    MpServer
    -0.70
    ancer
    -0.70
    ulo
    -0.69
    wealth
    -0.69
    sembly
    -0.68
    bara
    -0.68
    stated
    -0.67
    POSITIVE LOGITS
    fulness
    0.82
     someday
    0.79
    iam
    0.76
     be
    0.75
    fully
    0.74
     continue
    0.74
    ful
    0.69
     suffice
    0.68
     doubtless
    0.68
     soon
    0.67
    Activations Density 0.030%

    No Known Activations