© 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. 7192
    Prev
    Next
    INDEX
    Explanations

    names of famous individuals

    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
    556
    +0.12
    0.6%
    354
    +0.11
    0.5%
    79
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    232
    +0.11
    0.02
    556
    +0.10
    0.02
    Negative Logits
    erest
    -0.87
    zona
    -0.84
     CTR
    -0.71
     minors
    -0.70
     stabilization
    -0.69
    nect
    -0.67
    SHIP
    -0.66
     Palest
    -0.65
    mental
    -0.65
    igators
    -0.64
    POSITIVE LOGITS
     Cooke
    0.78
     Conan
    0.76
     Browne
    0.76
     Leigh
    0.75
     Sir
    0.75
     Hoo
    0.73
     Keane
    0.72
     Canterbury
    0.72
     Thatcher
    0.71
     Murray
    0.70
    Activations Density 0.045%

    No Known Activations