© 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. 19573
    Prev
    Next
    INDEX
    Explanations

    exercises and body parts related to physical fitness

    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
    754
    +0.12
    0.5%
    624
    +0.11
    0.5%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    754
    +0.12
    0.03
    574
    +0.11
    0.03
    99
    +0.10
    0.03
    Negative Logits
     Hoover
    -0.82
    yrinth
    -0.74
     Clover
    -0.74
     Kafka
    -0.72
     Ans
    -0.67
     Dickens
    -0.67
     Booth
    -0.66
     Doodle
    -0.65
     Nex
    -0.64
     Jarrett
    -0.63
    POSITIVE LOGITS
    guards
    1.43
    guard
    1.23
    building
    1.22
    builders
    1.19
    builder
    1.12
    weight
    1.10
     politic
    1.04
    parts
    1.02
    wash
    0.92
    fat
    0.90
    Activations Density 0.036%

    No Known Activations