© 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. 1280
    Prev
    Next
    INDEX
    Explanations

    mentions of ceasefire violations

    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
    447
    +0.15
    0.7%
    481
    +0.11
    0.5%
    317
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.15
    0.04
    0
    +0.11
    0.04
    288
    +0.10
    0.05
    Negative Logits
    HH
    -0.80
    Inv
    -0.77
    Widget
    -0.75
    Exper
    -0.73
    Offline
    -0.72
    Compan
    -0.69
    Stud
    -0.68
    Jess
    -0.68
    Iv
    -0.68
    Sym
    -0.67
    POSITIVE LOGITS
     ray
    0.77
     law
    0.71
     offending
    0.68
     pot
    0.68
     fry
    0.67
     justice
    0.66
     dope
    0.66
     care
    0.65
    -
    0.65
     borne
    0.64
    Activations Density 0.252%

    No Known Activations