© 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 EvalsExportsinterp-engineNEWAPI 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. 16686
    Prev
    Next
    INDEX
    Explanations

    profane language

    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
    50
    +0.10
    0.4%
    666
    +0.10
    0.4%
    620
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.10
    0.02
    284
    +0.10
    0.01
    326
    +0.10
    0.01
    Negative Logits
    HCR
    -0.77
    NetMessage
    -0.71
    fman
    -0.70
     Expend
    -0.66
    PsyNetMessage
    -0.65
    BIL
    -0.65
    arb
    -0.64
     Somers
    -0.62
    ervation
    -0.61
    Cour
    -0.60
    POSITIVE LOGITS
    bags
    1.08
    heads
    1.06
    loads
    0.98
    storm
    0.98
    lords
    0.96
    holes
    0.95
    lord
    0.94
    posts
    0.92
     detector
    0.92
    shit
    0.91
    Activations Density 0.029%

    No Known Activations