© 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. 12010
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical sensations or bodily characteristics

    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
    314
    +0.12
    0.6%
    161
    +0.11
    0.5%
    649
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.12
    0.01
    326
    +0.11
    0.01
    428
    +0.11
    0.01
    Negative Logits
     Educational
    -0.66
     Soros
    -0.65
    vernment
    -0.65
     Hammond
    -0.64
     Hof
    -0.64
    agall
    -0.64
     Nex
    -0.63
    AMI
    -0.61
     Developers
    -0.61
     Peg
    -0.60
    POSITIVE LOGITS
    lings
    1.17
    bags
    1.00
    meat
    0.98
    ly
    0.95
    shed
    0.93
    thirst
    0.92
    lesh
    0.91
    roots
    0.90
    mares
    0.89
    grave
    0.89
    Activations Density 0.024%

    No Known Activations