© 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. 9-RES-JB
    11. 18257
    Prev
    Next
    INDEX
    Explanations

    terms related to rules, regulations, and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal, governmental, and constitutional matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utenberg
    -0.80
    ahime
    -0.80
    anmar
    -0.75
    psey
    -0.64
    ilib
    -0.64
    ĸļ
    -0.63
    itone
    -0.63
    maxwell
    -0.62
    escription
    -0.61
    anchester
    -0.61
    POSITIVE LOGITS
     whatsoever
    1.91
     imaginable
    1.45
    soever
    1.30
     conceivable
    1.09
     except
    0.99
     anywhere
    0.88
     EVER
    0.85
    respect
    0.83
     besides
    0.81
    related
    0.81
    Activations Density 0.268%

    No Known Activations