© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2680
    Prev
    Next
    INDEX
    Explanations

    statements or conclusions related to research findings

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically closing parentheses

    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
    ifying
    -0.69
    bucks
    -0.67
    ellery
    -0.65
     scen
    -0.64
    ication
    -0.64
    icating
    -0.64
    enture
    -0.63
     Nanto
    -0.62
    iru
    -0.61
    dra
    -0.61
    POSITIVE LOGITS
    mosp
    0.78
     ILCS
    0.71
     Entered
    0.71
    zip
    0.66
    ypes
    0.66
    ::::::::
    0.66
    NRS
    0.64
    IPS
    0.63
    errors
    0.62
    println
    0.62
    Activations Density 0.075%

    No Known Activations