© 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. 18890
    Prev
    Next
    INDEX
    Explanations

    words related to technology and information

    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
    718
    +0.13
    0.6%
    253
    +0.10
    0.5%
    133
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.13
    0.04
    133
    +0.10
    0.04
    253
    +0.10
    0.04
    Negative Logits
    rend
    -0.88
    anu
    -0.73
    ugal
    -0.73
    HCR
    -0.71
    ync
    -0.71
    utra
    -0.69
    asus
    -0.68
    reating
    -0.67
    othy
    -0.65
    ractor
    -0.64
    POSITIVE LOGITS
    handed
    1.02
     though
    0.99
    handedly
    0.98
     tho
    0.88
     remotely
    0.85
    iating
    0.70
    este
    0.70
    iates
    0.69
     numbered
    0.68
    ITY
    0.65
    Activations Density 0.048%

    No Known Activations