© 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. 18287
    Prev
    Next
    INDEX
    Explanations

    phrases related to contributing to a report or article

    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
    214
    +0.13
    0.6%
    373
    +0.11
    0.5%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.13
    0.02
    767
    +0.11
    0.02
    412
    +0.09
    0.01
    Negative Logits
    é¾įåĸļ士
    -0.82
    gone
    -0.79
    Reloaded
    -0.71
    stood
    -0.69
    é¾įå¥ij士
    -0.65
    coming
    -0.64
    NetMessage
    -0.64
    lite
    -0.63
     Majesty
    -0.63
    within
    -0.60
    POSITIVE LOGITS
     drafts
    0.82
    letters
    0.79
     reporting
    0.77
     Coverage
    0.74
     reprinted
    0.71
    hovah
    0.71
     editorial
    0.70
     VIDE
    0.70
     Sawyer
    0.70
    ocument
    0.69
    Activations Density 0.068%

    No Known Activations