© 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. 7-RES-JB
    11. 11840
    Prev
    Next
    INDEX
    Explanations

    titles or headings in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific character or entity, identified by a unique symbol

    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
    ctors
    -0.79
    vier
    -0.77
    ussian
    -0.74
    lder
    -0.72
     arrang
    -0.70
     strugg
    -0.69
    iple
    -0.69
    thur
    -0.69
    getic
    -0.68
     oun
    -0.67
    POSITIVE LOGITS
    LESS
    0.74
    SOURCE
    0.72
    ï¸ı
    0.72
    ¯
    0.68
    dayName
    0.62
     Illustrated
    0.61
     Ibid
    0.61
     wherein
    0.61
     whereby
    0.60
     namely
    0.60
    Activations Density 0.167%

    No Known Activations