© 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 12288
    9. 8-RES_FS12288-JB
    11. 10656
    Prev
    Next
    INDEX
    Explanations

    proper names and titles within a text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    314
    +0.20
    0.9%
    102
    +0.13
    0.6%
    160
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.20
    0.06
    160
    +0.13
    0.06
    314
    +0.13
    0.01
    Negative Logits
     synd
    -0.76
     succession
    -0.75
     affiliate
    -0.75
     logging
    -0.73
     appointment
    -0.72
     candles
    -0.72
     rental
    -0.71
     posting
    -0.71
     Alger
    -0.71
     chair
    -0.69
    POSITIVE LOGITS
    inventoryQuantity
    1.26
    Big
    1.19
    cheat
    1.15
    Golden
    1.14
    Fuck
    1.13
    Hope
    1.12
    Never
    1.12
    their
    1.12
    Hello
    1.11
    Hey
    1.11
    Activations Density 0.154%

    No Known Activations