© 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. 8726
    Prev
    Next
    INDEX
    Explanations

    specific terms or phrases regarding plans or organized activities

    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
    133
    +0.11
    0.5%
    45
    +0.11
    0.5%
    609
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    698
    +0.11
    0.02
    466
    +0.11
    0.02
    133
    +0.10
    0.02
    Negative Logits
     Chin
    -0.73
    raph
    -0.71
    aser
    -0.70
     Beir
    -0.66
    otrop
    -0.64
     Stur
    -0.64
     Pine
    -0.64
     curs
    -0.63
    oresc
    -0.63
     Rosen
    -0.62
    POSITIVE LOGITS
    !'
    1.43
    !.
    1.42
    !,
    1.41
    !:
    1.36
    !
    1.35
    !'"
    1.24
    !"
    1.16
    !".
    1.14
    !",
    1.14
    !/
    1.12
    Activations Density 0.116%

    No Known Activations