© 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. 10-RES-JB
    11. 1382
    Prev
    Next
    INDEX
    Explanations

    descriptions of software bug fixes involving specific technical information

    oai_token-act-pair · gpt-3.5-turbo

    references to software bugs and technical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    —-
    -0.85
     ÂŃ
    -0.83
    )—
    -0.77
    llah
    -0.76
    reviewed
    -0.75
    "—
    -0.73
    —
    -0.73
    adies
    -0.70
     duly
    -0.68
    Äĵ
    -0.68
    POSITIVE LOGITS
     tooltip
    1.21
     incorrectly
    1.13
     popup
    1.06
     respawn
    1.02
     incorrect
    1.01
     GUI
    0.97
     errone
    0.96
     HUD
    0.93
     cursor
    0.92
     dialog
    0.89
    Activations Density 0.211%

    No Known Activations