© 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. 9-RES-JB
    11. 4547
    Prev
    Next
    INDEX
    Explanations

    capitalized abbreviations or acronyms preceded by "BE"

    oai_token-act-pair · gpt-3.5-turbo

    instances of empty segments or placeholders in the text

    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
    kson
    -0.68
    geist
    -0.66
    iors
    -0.63
    opter
    -0.63
    raints
    -0.63
    owicz
    -0.62
    ãĤ¡
    -0.62
    strings
    -0.58
    selves
    -0.58
     Franks
    -0.58
    POSITIVE LOGITS
    VILLE
    1.33
    MAN
    1.33
     CITY
    1.28
    STON
    1.25
    INGTON
    1.24
    LAND
    1.24
    COL
    1.23
    OIL
    1.22
    VIEW
    1.20
    TON
    1.20
    Activations Density 0.116%

    No Known Activations