© 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. 37275
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to entertainment and specific organizations

    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
    377
    +0.13
    0.6%
    447
    +0.12
    0.6%
    268
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.02
    288
    +0.12
    0.03
    343
    +0.11
    0.02
    Negative Logits
    apers
    -0.95
    essee
    -0.93
    iple
    -0.85
    phis
    -0.83
    areth
    -0.81
    oppable
    -0.80
    itan
    -0.79
    oting
    -0.79
    adra
    -0.78
    uable
    -0.76
    POSITIVE LOGITS
     Ascension
    0.66
     Triangle
    0.64
    EGIN
    0.64
    Reloaded
    0.63
    ruary
    0.62
    axter
    0.61
    wana
    0.60
    ãĥ©ãĥ³
    0.59
     Unch
    0.59
     Initi
    0.59
    Activations Density 0.053%

    No Known Activations