© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20919
    Prev
    Next
    INDEX
    Explanations

    actions related to monitoring or verifying something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "check" in various contexts

    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
    ufact
    -0.74
    theless
    -0.73
    ãĤ´ãĥ³
    -0.71
    usable
    -0.69
    é¾įå
    -0.68
    \":
    -0.68
    ña
    -0.68
    ĸļ
    -0.67
    Sin
    -0.66
    ãĥĢ
    -0.66
    POSITIVE LOGITS
     whether
    1.04
    lists
    0.96
    boxes
    0.96
    mate
    0.96
     IDs
    0.95
     out
    0.93
     if
    0.82
     boxes
    0.77
     Yelp
    0.77
     into
    0.76
    Activations Density 0.028%

    No Known Activations