© 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. 9260
    Prev
    Next
    INDEX
    Explanations

    solutions or ways to address various problems or issues

    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
    308
    +0.11
    0.5%
    473
    +0.09
    0.4%
    724
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.11
    0.02
    614
    +0.09
    0.02
    51
    +0.09
    0.02
    Negative Logits
    prints
    -0.73
     Bones
    -0.70
    ardy
    -0.69
     livest
    -0.68
    head
    -0.68
    rob
    -0.67
     cloves
    -0.63
     Saud
    -0.61
    rolled
    -0.61
    ammy
    -0.61
    POSITIVE LOGITS
    Solution
    0.92
     solutions
    0.90
    olution
    0.87
     solution
    0.86
     solve
    0.86
    olutions
    0.81
     thereto
    0.80
    acea
    0.76
     Solution
    0.74
     solving
    0.74
    Activations Density 0.027%

    No Known Activations