© 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. 1339
    Prev
    Next
    INDEX
    Explanations

    company names and information related to business deals

    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
    578
    +0.13
    0.6%
    145
    +0.12
    0.6%
    648
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    578
    +0.13
    0.04
    648
    +0.12
    0.04
    659
    +0.11
    0.04
    Negative Logits
     GOODMAN
    -0.72
    æ©Ł
    -0.72
    æ©
    -0.70
    MpServer
    -0.69
    taboola
    -0.68
     Gleaming
    -0.68
     Lauder
    -0.67
     contrace
    -0.66
    NESS
    -0.64
     horizont
    -0.63
    POSITIVE LOGITS
    ossible
    1.50
    ulse
    1.38
    redict
    1.32
    ilot
    1.31
    resents
    1.31
    olitan
    1.25
    ivot
    1.25
    overty
    1.23
    ixels
    1.22
    ossession
    1.20
    Activations Density 0.086%

    No Known Activations