© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7813
    Prev
    Next
    INDEX
    Explanations

    Geographical locations and companies or organizations with notable associations

    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
    29
    +0.10
    0.4%
    712
    +0.10
    0.4%
    184
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.05
    388
    +0.10
    0.04
    24
    +0.09
    0.04
    Negative Logits
     theoret
    -0.76
     perjury
    -0.73
     theorist
    -0.71
     cuff
    -0.70
     disarm
    -0.66
     slippery
    -0.64
     hump
    -0.64
     stretch
    -0.64
     warr
    -0.64
     firefighter
    -0.63
    POSITIVE LOGITS
     Ltd
    0.75
     Labs
    0.74
    *.
    0.74
    orum
    0.72
    Laun
    0.70
    uca
    0.69
    Ħ¢
    0.67
    Corp
    0.67
     Enterprises
    0.66
    qa
    0.65
    Activations Density 0.314%

    No Known Activations