© 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. 8-RES-JB
    11. 19426
    Prev
    Next
    INDEX
    Explanations

    technical steps or instructions written in a step-by-step format

    oai_token-act-pair · gpt-3.5-turbo

    structured steps or items in a process or list format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .","
    -0.76
     cle
    -0.61
     bonded
    -0.61
    rop
    -0.60
    ``
    -0.60
    assets
    -0.58
    omorphic
    -0.58
     Mond
    -0.58
     Spac
    -0.57
     gent
    -0.56
    POSITIVE LOGITS
    jamin
    0.97
    Marginal
    0.79
    etheless
    0.77
    dinand
    0.77
    theless
    0.76
    ercise
    0.73
    resa
    0.73
    arnaev
    0.72
    asionally
    0.72
    inki
    0.70
    Activations Density 0.186%

    No Known Activations