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 1536
    5. 8-RES_FS1536-JB
    6. 377
    Prev
    Next
    INDEX
    Explanations

    mentions of various football clubs, players, and matches

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    373
    +0.18
    0.8%
    546
    +0.12
    0.5%
    725
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.18
    -0.07
    284
    +0.12
    0.13
    232
    +0.10
    0.11
    Negative Logits
    vernment
    -0.71
    ahon
    -0.63
    é¾įå
    -0.60
    hent
    -0.57
     Attribution
    -0.57
    ynt
    -0.57
    bring
    -0.57
    Frames
    -0.56
    adden
    -0.56
    binding
    -0.56
    POSITIVE LOGITS
    wagen
    0.67
    cius
    0.65
    ciating
    0.63
    ilda
    0.62
    wick
    0.61
    BuyableInstoreAndOnline
    0.60
    Royal
    0.60
    Ĥ¬
    0.59
     Despair
    0.58
    ieri
    0.57
    Activations Density 3.322%

    No Known Activations