© 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. 11-RES-JB
    6. 22319
    Prev
    Next
    INDEX
    Explanations

    sentences describing physical actions and movements

    oai_token-act-pair · gpt-3.5-turbo

    instances of a comma in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.83
    ¥µ
    -0.75
    export
    -0.71
    ename
    -0.69
    vre
    -0.69
    conom
    -0.68
    enz
    -0.67
    ãĤ¦ãĤ¹
    -0.65
    Probably
    -0.65
    =(
    -0.64
    POSITIVE LOGITS
     however
    1.03
     gunshots
    0.85
     onlook
    0.82
     she
    0.80
     passers
    0.78
     someone
    0.78
     Sergeant
    0.78
     he
    0.77
     they
    0.76
     paramedics
    0.74
    Activations Density 0.171%

    No Known Activations