© 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. 8-RES-JB
    11. 8011
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols, specifically related to ratings and systems commands

    oai_token-act-pair · gpt-3.5-turbo

    sequences of letters and numbers typically associated with identifiers or codes

    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
     domest
    -0.66
     cultivating
    -0.55
     birthplace
    -0.49
     occupations
    -0.49
     nurt
    -0.48
     butcher
    -0.46
    cephal
    -0.46
     autonomous
    -0.46
     temperament
    -0.46
    Thumbnail
    -0.45
    POSITIVE LOGITS
    xxxxxxxx
    0.65
    OTAL
    0.64
     TOTAL
    0.63
    %"
    0.63
    TION
    0.62
     Coffin
    0.59
    !.
    0.59
    %.
    0.59
    <|endoftext|>
    0.58
     WRITE
    0.54
    Activations Density 0.565%

    No Known Activations