© 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. 20362
    Prev
    Next
    INDEX
    Explanations

    words related to physical conditions or states of disorder or degradation

    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
    497
    +0.11
    0.5%
    629
    +0.10
    0.5%
    135
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.04
    35
    +0.10
    0.03
    678
    +0.10
    0.03
    Negative Logits
    OTOS
    -0.75
     srf
    -0.71
    rises
    -0.66
     Camer
    -0.66
    OTO
    -0.63
    role
    -0.61
    nect
    -0.61
    itability
    -0.60
    lia
    -0.60
    ilater
    -0.59
    POSITIVE LOGITS
     heap
    0.86
    ishly
    0.84
     piles
    0.84
    meat
    0.81
    enance
    0.77
    punk
    0.77
     rotting
    0.76
     stains
    0.74
    gery
    0.74
     sacks
    0.74
    Activations Density 0.160%

    No Known Activations