Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 21504
    Prev
    Next
    INDEX
    Explanations

    words related to technical instructions and procedures

    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
    157
    +0.13
    0.6%
    314
    +0.12
    0.6%
    20
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.13
    0.08
    154
    +0.12
    0.07
    439
    +0.12
    0.07
    Negative Logits
     cryst
    -0.69
     microw
    -0.68
     metaphor
    -0.66
     decomp
    -0.66
     carbohyd
    -0.65
     elim
    -0.64
     mathemat
    -0.63
     scrim
    -0.63
     unbeliev
    -0.62
     envelop
    -0.62
    POSITIVE LOGITS
    s
    1.73
    ski
    1.24
    sf
    1.22
    ship
    1.16
    sen
    1.11
    sg
    1.08
    tal
    1.06
    ships
    1.05
    ses
    1.04
    sa
    1.04
    Activations Density 0.163%

    No Known Activations