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

    Neuronpedia

    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. 238
    Prev
    Next
    INDEX
    Explanations

    years

    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
    451
    +0.12
    0.5%
    748
    +0.12
    0.5%
    741
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.12
    0.06
    544
    +0.12
    0.04
    483
    +0.10
    0.05
    Negative Logits
    ums
    -0.73
    ounding
    -0.69
    advertisement
    -0.66
    habi
    -0.65
    natureconservancy
    -0.63
    cffffcc
    -0.61
    vana
    -0.60
    iggins
    -0.60
    MpServer
    -0.60
    voc
    -0.58
    POSITIVE LOGITS
     they
    1.25
     there
    1.17
     we
    1.16
     it
    1.09
     THEY
    1.06
     nobody
    1.00
     he
    0.97
     THERE
    0.95
    there
    0.92
     she
    0.88
    Activations Density 0.348%

    No Known Activations