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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12550
    Prev
    Next
    INDEX
    Explanations

    sections of documents that are citations, references, or details about where data is derived from

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of parentheses in the text

    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
     whip
    -0.74
     glare
    -0.73
     reve
    -0.72
     baffled
    -0.72
     hot
    -0.72
     pen
    -0.71
     retard
    -0.71
     daily
    -0.70
     vit
    -0.70
     tricked
    -0.70
    POSITIVE LOGITS
    see
    1.75
    Figure
    1.57
    emphasis
    1.54
    although
    1.45
    including
    1.43
    except
    1.42
    sic
    1.42
    Fig
    1.41
    according
    1.38
    excluding
    1.37
    Activations Density 0.154%

    No Known Activations