© 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. 7826
    Prev
    Next
    INDEX
    Explanations

    mentions of proposals or initiatives, potentially related to legal or healthcare contexts

    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
    288
    +0.14
    0.6%
    459
    +0.10
    0.5%
    461
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.14
    0.02
    637
    +0.10
    0.01
    444
    +0.10
    0.01
    Negative Logits
    keeper
    -0.77
    soever
    -0.75
     Peaks
    -0.68
     Carbuncle
    -0.68
     Waters
    -0.63
     pores
    -0.63
     Maw
    -0.63
     Confederacy
    -0.62
     Caribbean
    -0.62
    Interstitial
    -0.62
    POSITIVE LOGITS
    ulsive
    1.28
    aganda
    1.24
    itious
    1.19
    onents
    1.19
    ylene
    1.18
    ulsion
    1.13
    ractor
    1.13
    onent
    1.12
    osed
    1.08
    ensity
    1.08
    Activations Density 0.017%

    No Known Activations