© 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. 18544
    Prev
    Next
    INDEX
    Explanations

    names of people or places from various regions

    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
    623
    +0.13
    0.6%
    195
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.04
    406
    +0.11
    0.03
    284
    +0.11
    0.03
    Negative Logits
    sonian
    -0.74
    ongyang
    -0.70
     Lauderdale
    -0.65
    pecially
    -0.64
    monton
    -0.63
    suit
    -0.63
    pn
    -0.63
    PLAY
    -0.63
    REE
    -0.62
    PRES
    -0.61
    POSITIVE LOGITS
    igans
    1.20
    thal
    1.13
    ova
    1.05
    ensis
    1.05
    ufact
    1.02
    ning
    1.02
    ned
    1.02
    ews
    1.01
    ovich
    1.00
    ese
    1.00
    Activations Density 0.074%

    No Known Activations