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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12199
    Prev
    Next
    INDEX
    Explanations

    mentions of Fidel Castro

    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
    471
    +0.13
    0.6%
    728
    +0.12
    0.6%
    288
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.13
    0.01
    367
    +0.12
    0.01
    288
    +0.12
    0.01
    Negative Logits
    #$
    -0.76
    roads
    -0.69
    apeshifter
    -0.67
    amera
    -0.67
     DRAG
    -0.66
    venants
    -0.65
    PASS
    -0.64
    Ħ¢
    -0.64
    yout
    -0.63
    rules
    -0.59
    POSITIVE LOGITS
     Castro
    1.13
    ius
    1.03
    itary
    0.95
     Chavez
    0.86
    uvian
    0.86
     Ramos
    0.84
    acies
    0.84
    icates
    0.83
    iment
    0.83
    iments
    0.83
    Activations Density 0.003%

    No Known Activations