© 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. 12152
    Prev
    Next
    INDEX
    Explanations

    words related to simplifying processes or concepts

    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
    658
    +0.12
    0.5%
    421
    +0.11
    0.5%
    635
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.12
    0.02
    455
    +0.11
    0.02
    99
    +0.10
    0.02
    Negative Logits
    vine
    -0.80
    reon
    -0.77
    mir
    -0.74
    igion
    -0.66
    CVE
    -0.66
    rings
    -0.65
    AIDS
    -0.65
    wine
    -0.65
    hips
    -0.63
    vance
    -0.63
    POSITIVE LOGITS
    Catalog
    0.87
     simplicity
    0.82
     simplify
    0.81
     simplified
    0.78
     formulation
    0.76
    ahime
    0.75
    istically
    0.75
    ose
    0.74
     explanations
    0.74
     streamlined
    0.73
    Activations Density 0.070%

    No Known Activations