© 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 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. 7-RES-JB
    11. 21163
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to vectors

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and jargon related to computing or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arij
    -0.67
    gewater
    -0.63
    err
    -0.62
    isSpecialOrderable
    -0.59
    kay
    -0.58
    Rog
    -0.56
     Hob
    -0.55
    APP
    -0.54
     stew
    -0.53
    issues
    -0.53
    POSITIVE LOGITS
     "$:/
    0.75
    shapeshifter
    0.66
    urations
    0.63
    )=(
    0.58
    rals
    0.58
     rgb
    0.56
    sson
    0.56
     guiName
    0.56
    piracy
    0.56
     supra
    0.55
    Activations Density 0.310%

    No Known Activations