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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 26228
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "ane" 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
    99
    +0.15
    0.7%
    453
    +0.11
    0.5%
    35
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.15
    0.02
    515
    +0.11
    0.01
    406
    +0.10
    0.01
    Negative Logits
    enance
    -0.76
    rador
    -0.76
    s
    -0.76
     Carbuncle
    -0.75
    enegger
    -0.74
     Seym
    -0.73
    irements
    -0.73
    spection
    -0.71
    awaru
    -0.70
    olicy
    -0.69
    POSITIVE LOGITS
    gas
    0.99
    jad
    0.92
    vil
    0.82
    hyde
    0.81
    ffe
    0.80
    vich
    0.79
    venue
    0.77
    cia
    0.77
    IRO
    0.76
    cember
    0.75
    Activations Density 0.009%

    No Known Activations