© 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. 7-RES-JB
    6. 15371
    Prev
    Next
    INDEX
    Explanations

    instances where the text is addressing the reader directly with a persuasive or instructive tone

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their contextual use in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃŃs
    -0.62
    stice
    -0.62
    ilege
    -0.61
    lier
    -0.61
    eker
    -0.60
    retty
    -0.60
    ascus
    -0.59
    ı
    -0.59
     thous
    -0.58
    Ùħ
    -0.58
    POSITIVE LOGITS
    é¾įå¥ij士
    0.66
     Spoiler
    0.66
    cens
    0.65
     ie
    0.60
     Krug
    0.59
     Particularly
    0.59
    please
    0.58
    padding
    0.57
     Expect
    0.57
    csv
    0.57
    Activations Density 0.504%

    No Known Activations