© 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 12288
    9. 8-RES_FS12288-JB
    11. 400
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences, emotions, and observations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    762
    +0.16
    0.7%
    545
    +0.11
    0.5%
    468
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.16
    0.11
    545
    +0.11
    0.05
    70
    +0.09
    0.07
    Negative Logits
     unison
    -0.72
    moil
    -0.70
     Authors
    -0.69
    hub
    -0.69
     collectively
    -0.67
    selves
    -0.66
     respectively
    -0.63
     jointly
    -0.61
     Thou
    -0.60
     ballots
    -0.60
    POSITIVE LOGITS
     himself
    1.45
     Himself
    1.01
     his
    0.88
     fuckin
    0.78
     remorse
    0.78
    Jr
    0.77
     sul
    0.77
     alright
    0.72
     me
    0.72
     us
    0.65
    Activations Density 0.995%

    No Known Activations