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. 40061
    Prev
    Next
    INDEX
    Explanations

    cities and locations relevant to the context of the document

    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
    481
    +0.34
    1.7%
    447
    +0.23
    1.2%
    219
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.34
    0.05
    219
    +0.23
    0.05
    752
    +0.12
    0.06
    Negative Logits
    rations
    -0.67
     sacrific
    -0.65
    rious
    -0.64
    ãĤ¯
    -0.63
    akable
    -0.60
    henko
    -0.60
    zes
    -0.58
    ifix
    -0.56
    utations
    -0.56
     contr
    -0.56
    POSITIVE LOGITS
     County
    1.03
     suburb
    0.98
     City
    0.94
     suburbs
    0.94
     Heights
    0.93
    shire
    0.88
     Township
    0.87
     Harbour
    0.86
     Chinatown
    0.85
     Harbor
    0.85
    Activations Density 0.099%

    No Known Activations