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 49152
    5. 8-RES_FS49152-JB
    6. 26394
    Prev
    Next
    INDEX
    Explanations

    references to the word "drive" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    195
    +0.15
    0.7%
    377
    +0.12
    0.6%
    201
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.15
    0.01
    326
    +0.12
    0.01
    201
    +0.10
    0.01
    Negative Logits
     Authority
    -0.78
    OTOS
    -0.69
    RON
    -0.68
    ENTS
    -0.64
    å§«
    -0.64
     Mutual
    -0.63
    FactoryReloaded
    -0.62
     GOODMAN
    -0.62
    IONS
    -0.62
     Unch
    -0.61
    POSITIVE LOGITS
    ppings
    1.26
    zzle
    1.23
    vable
    1.22
    zz
    1.20
    pped
    1.17
    zzy
    1.09
    pping
    1.03
    vin
    1.01
    ps
    1.00
    quet
    0.97
    Activations Density 0.003%

    No Known Activations