© 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. 13482
    Prev
    Next
    INDEX
    Explanations

    specific tokens related to the word "brand"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "br" 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
     Relief
    -0.70
     FTA
    -0.67
     Modest
    -0.61
     Aman
    -0.61
     Mercury
    -0.60
     Contra
    -0.59
    ral
    -0.59
     Furious
    -0.57
     caps
    -0.57
     lying
    -0.57
    POSITIVE LOGITS
    ackets
    1.58
    acket
    1.46
    anches
    1.42
    igham
    1.25
    anch
    1.24
    ushed
    1.21
    addock
    1.20
    onson
    1.18
    ushes
    1.17
    ushing
    1.17
    Activations Density 0.016%

    No Known Activations