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. 23964
    Prev
    Next
    INDEX
    Explanations

    instances of the term "man" that relate to numerical counts in various contexts

    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
    515
    +0.14
    0.6%
    291
    +0.12
    0.6%
    38
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.14
    0.02
    247
    +0.12
    0.02
    515
    +0.11
    0.02
    Negative Logits
    schild
    -0.93
    Girls
    -0.78
    Birth
    -0.77
    PsyNetMessage
    -0.73
    Neigh
    -0.73
    rss
    -0.72
    DATA
    -0.71
    INTON
    -0.69
    Daily
    -0.68
    ython
    -0.67
    POSITIVE LOGITS
    hunt
    1.16
    agers
    1.09
    ifest
    0.96
    hood
    0.94
    nered
    0.94
    oeuv
    0.93
    chu
    0.88
    eu
    0.88
    uscript
    0.88
    abases
    0.87
    Activations Density 0.022%

    No Known Activations