© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 22136
    Prev
    Next
    INDEX
    Explanations

    mentions of "Charlie," likely referring to the Charlie Hebdo publication or its related context

    oai_token-act-pair · gpt-4o-miniTriggered 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
    609
    +0.10
    0.5%
    686
    +0.10
    0.5%
    200
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.10
    0.01
    1
    +0.10
    0.01
    200
    +0.08
    0.01
    Negative Logits
    awaru
    -0.91
    ographical
    -0.84
    ĺħ
    -0.81
    ahime
    -0.81
    ersed
    -0.79
    senal
    -0.79
    nesota
    -0.77
    ItemTracker
    -0.77
    dyl
    -0.76
    ules
    -0.76
    POSITIVE LOGITS
     Hebdo
    1.37
     Sheen
    1.08
     Manson
    0.91
     Cha
    0.91
     Brown
    0.87
     Daniels
    0.82
    TER
    0.82
     Dent
    0.81
    anut
    0.79
     Pace
    0.79
    Activations Density 0.012%

    No Known Activations