© 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. 37279
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes and actions

    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
    135
    +0.11
    0.5%
    160
    +0.11
    0.5%
    666
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.11
    0.01
    460
    +0.11
    0.01
    135
    +0.10
    0.01
    Negative Logits
    irie
    -0.74
     Recommend
    -0.65
    nesday
    -0.64
    emort
    -0.62
     cig
    -0.61
    poon
    -0.60
     Cout
    -0.60
     Speedway
    -0.58
    erred
    -0.58
     Redd
    -0.58
    POSITIVE LOGITS
    ions
    0.79
     process
    0.76
    igating
    0.73
    igation
    0.73
     thereof
    0.71
    ivity
    0.70
    ional
    0.69
    ________________________________________________________________
    0.69
    aday
    0.67
    ivism
    0.67
    Activations Density 0.008%

    No Known Activations