© 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. 9870
    Prev
    Next
    INDEX
    Explanations

    dollar amounts and financial information

    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
    393
    +0.13
    0.6%
    88
    +0.09
    0.4%
    101
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    572
    +0.13
    0.04
    669
    +0.09
    0.03
    362
    +0.09
    0.04
    Negative Logits
    ptive
    -0.70
    vable
    -0.70
    case
    -0.69
    zzle
    -0.65
    agnar
    -0.64
    rollers
    -0.63
    matic
    -0.63
    urden
    -0.63
    headed
    -0.62
    zers
    -0.61
    POSITIVE LOGITS
     sorts
    1.28
     hers
    1.11
     ours
    1.08
     mine
    0.96
     theirs
    0.96
     yours
    0.85
     Nanto
    0.80
    Camp
    0.74
     Mine
    0.72
    Boost
    0.67
    Activations Density 0.118%

    No Known Activations