© 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. 11167
    Prev
    Next
    INDEX
    Explanations

    instructional text or guidelines for actions

    oai_token-act-pair · gpt-3.5-turbo

    references to reading or reviewing instructional materials

    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
    antle
    -0.64
     promotions
    -0.62
    claimed
    -0.62
    ayn
    -0.60
     vows
    -0.59
     euth
    -0.59
    ãĤ´ãĥ³
    -0.58
    bots
    -0.58
     hostage
    -0.57
    announced
    -0.57
    POSITIVE LOGITS
     read
    1.41
     reading
    1.24
     skim
    1.24
    read
    1.23
     download
    1.20
     browse
    1.12
     CLICK
    1.12
     consult
    1.11
     scroll
    1.10
     READ
    1.10
    Activations Density 0.313%

    No Known Activations