© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    6. 17111
    Prev
    Next
    INDEX
    Explanations

    books, movies, music, and other forms of media

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "AM" and related forms or variations

    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
     Reincarn
    -0.67
    perty
    -0.66
    ÙIJ
    -0.65
    Ö¼
    -0.64
    catentry
    -0.61
     thous
    -0.61
    =-=-
    -0.59
    ĨĴ
    -0.59
    Versions
    -0.59
    landish
    -0.59
    POSITIVE LOGITS
    heed
    0.91
    gow
    0.83
    ibrary
    0.80
    oyd
    0.80
    ounge
    0.79
    henko
    0.79
    emort
    0.76
    omez
    0.75
    uckles
    0.73
    inen
    0.72
    Activations Density 0.587%

    No Known Activations