© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 3374
    Prev
    Next
    INDEX
    Explanations

    keywords related to official documents or paperwork, specifically those named "memorandum"

    oai_token-act-pair · gpt-3.5-turbo

    references to official documents and memoranda

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itably
    -0.96
    ihar
    -0.96
    riz
    -0.92
    ifax
    -0.92
    itable
    -0.90
    ité
    -0.84
    anza
    -0.82
    arson
    -0.82
    rets
    -0.80
    boys
    -0.80
    POSITIVE LOGITS
    andum
    1.15
    ĸļ
    0.97
     memorandum
    0.83
    isode
    0.82
    hift
    0.82
    RFC
    0.75
     Lumpur
    0.75
     assurance
    0.74
     mosqu
    0.72
     Consent
    0.70
    Activations Density 0.019%

    No Known Activations