© 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 49152
    9. 8-RES_FS49152-JB
    11. 41662
    Prev
    Next
    INDEX
    Explanations

    references to software and systems

    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
    481
    +0.13
    0.6%
    83
    +0.11
    0.5%
    517
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.13
    0.03
    517
    +0.11
    0.03
    83
    +0.10
    0.02
    Negative Logits
    ãĥ´ãĤ¡
    -0.91
    ãĥ´
    -0.84
    ãĥĦ
    -0.76
    Ļ½
    -0.73
    soType
    -0.70
    ãĥ¥
    -0.68
    oho
    -0.68
    ãĥĥãĥī
    -0.68
    angelo
    -0.67
    lehem
    -0.66
    POSITIVE LOGITS
     designation
    0.75
     technology
    0.70
     mode
    0.69
     specifications
    0.68
    psey
    0.67
     classification
    0.67
    /"
    0.66
     certification
    0.66
     capabilities
    0.66
     technologies
    0.65
    Activations Density 0.053%

    No Known Activations