© 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. 18675
    Prev
    Next
    INDEX
    Explanations

    mentions or references to financial transactions or numbers

    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
    274
    +0.12
    0.6%
    118
    +0.11
    0.5%
    575
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    118
    +0.12
    0.01
    690
    +0.11
    0.01
    232
    +0.10
    0.01
    Negative Logits
    glers
    -1.01
     MacArthur
    -0.73
     Hedge
    -0.70
     Grail
    -0.67
     ãĤµ
    -0.67
     Ibn
    -0.67
     Blaz
    -0.66
    MORE
    -0.66
    gerald
    -0.65
    draw
    -0.63
    POSITIVE LOGITS
    ises
    1.24
    iership
    1.18
    antle
    1.14
    ortal
    1.07
    otor
    1.07
    iere
    1.02
    inence
    1.01
    asks
    0.98
    ature
    0.98
    ilitary
    0.97
    Activations Density 0.023%

    No Known Activations