© 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
    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. 6536
    Prev
    Next
    INDEX
    Explanations

    mentions of group or organizational members

    oai_token-act-pair · gpt-3.5-turbo

    references to collective groups or memberships

    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
    ©¶æ
    -0.66
    Score
    -0.61
    uras
    -0.60
    BAT
    -0.60
    igslist
    -0.59
    BUS
    -0.59
     Tropical
    -0.58
    icer
    -0.58
    enegger
    -0.57
    ourses
    -0.56
    POSITIVE LOGITS
    hips
    1.61
    hip
    1.04
    doms
    0.97
     dues
    0.86
     of
    0.85
    meal
    0.79
     thereof
    0.79
    ials
    0.77
    board
    0.76
    member
    0.75
    Activations Density 0.065%

    No Known Activations