© 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 24576
    9. 8-RES_FS24576-JB
    11. 18818
    Prev
    Next
    INDEX
    Explanations

    measurements and geographical locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    570
    +0.11
    0.5%
    241
    +0.11
    0.5%
    35
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.11
    0.03
    35
    +0.11
    0.02
    678
    +0.10
    0.02
    Negative Logits
    ãĥĦ
    -0.69
    Ļ½
    -0.67
    ãĥ¥
    -0.67
    ãĤ¢ãĥ«
    -0.66
    (&
    -0.63
    tnc
    -0.63
    alogy
    -0.63
    omorphic
    -0.62
    natureconservancy
    -0.60
    omorph
    -0.58
    POSITIVE LOGITS
     apiece
    0.87
    ãĥİ
    0.73
    eous
    0.67
     reserved
    0.67
    +)
    0.66
     devoted
    0.65
    +.
    0.64
    ridges
    0.64
     dedicated
    0.61
     increments
    0.61
    Activations Density 0.053%

    No Known Activations