© 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. 1775
    Prev
    Next
    INDEX
    Explanations

    adjectives with a positive connotation

    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
    7
    +0.16
    0.7%
    659
    +0.14
    0.7%
    163
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.02
    7
    +0.14
    0.02
    163
    +0.11
    0.02
    Negative Logits
     disinfect
    -0.66
     Mobil
    -0.66
     Scotia
    -0.63
    backer
    -0.61
     Takeru
    -0.61
     Sheen
    -0.60
     Shards
    -0.59
     magnification
    -0.57
    VALUE
    -0.57
     Ethiop
    -0.57
    POSITIVE LOGITS
    ournal
    1.49
    ean
    1.05
    itsu
    1.04
    ournals
    1.02
    arro
    0.92
    olla
    0.89
    ewski
    0.86
    aha
    0.85
    unction
    0.83
    ungle
    0.83
    Activations Density 0.016%

    No Known Activations