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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 37130
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "re-" 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
    706
    +0.11
    0.5%
    503
    +0.11
    0.5%
    641
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    706
    +0.11
    0.03
    710
    +0.11
    0.03
    439
    +0.11
    0.02
    Negative Logits
    BuyableInstoreAndOnline
    -0.74
    DragonMagazine
    -0.72
     Eck
    -0.70
     Berm
    -0.70
     Pebble
    -0.69
     misunder
    -0.67
     Nest
    -0.67
    OSH
    -0.64
     Beir
    -0.64
     Isles
    -0.64
    POSITIVE LOGITS
    porter
    1.19
    actor
    1.19
    venge
    1.16
    brand
    1.11
    asons
    1.10
    venue
    1.10
    becca
    1.09
    vision
    1.09
    versible
    1.09
    ached
    1.08
    Activations Density 0.018%

    No Known Activations