© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10290
    Prev
    Next
    INDEX
    Explanations

    details related to language pronunciation and communication

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    284
    +0.11
    0.5%
    176
    +0.11
    0.5%
    6
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.03
    107
    +0.11
    0.02
    6
    +0.10
    0.02
    Negative Logits
     bonded
    -0.76
     betting
    -0.73
     narrowly
    -0.73
     bour
    -0.72
     sworn
    -0.70
     deliber
    -0.70
    leground
    -0.70
     plat
    -0.69
     dominated
    -0.68
     poaching
    -0.68
    POSITIVE LOGITS
    ãĤ
    1.71
    ãģ
    1.57
    ãĥ©
    1.54
    ãĤ¤
    1.53
    ãĥĩ
    1.53
    ãĤ¯
    1.52
    ãģĦ
    1.51
    ãĥ¼ãĥ
    1.51
    ãĥł
    1.50
    ãĥı
    1.49
    Activations Density 0.031%

    No Known Activations