© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 18616
    Prev
    Next
    INDEX
    Explanations

    short phrases interrupted by a comma and continued without a space

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, specifically commas, in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !'
    -0.64
    ',"
    -0.63
    !'"
    -0.62
    lette
    -0.61
    ikan
    -0.60
     guiActiveUnfocused
    -0.57
    lett
    -0.57
    allery
    -0.57
     enrichment
    -0.56
    '),
    -0.56
    POSITIVE LOGITS
     "âĢ¦
    1.18
     "'
    1.17
     "...
    1.16
     "[
    1.16
     "(
    1.12
     ""
    1.07
     "
    1.03
     "@
    1.03
     "#
    1.01
     quote
    0.95
    Activations Density 0.076%

    No Known Activations