© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 566
    Prev
    Next
    INDEX
    Explanations

    instances of the word "copped."

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate actions or processes involving physical movement or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    beit
    -0.63
     Schwar
    -0.60
     Siber
    -0.60
     ancest
    -0.59
     Antar
    -0.59
     Broncos
    -0.57
    è¯
    -0.57
     Fundamental
    -0.57
     [|
    -0.56
     phyl
    -0.56
    POSITIVE LOGITS
    olicy
    1.22
    inion
    0.90
    pping
    0.88
    artment
    0.88
    igious
    0.85
    onent
    0.84
    hod
    0.84
    pped
    0.83
    odcast
    0.82
    uppet
    0.82
    Activations Density 0.013%

    No Known Activations