© 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. 8-RES-JB
    11. 4051
    Prev
    Next
    INDEX
    Explanations

    notes or annotations indicated by "Note" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of "Note" and its variations, indicating detailed annotations or comments 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
    luaj
    -0.78
     Cosponsors
    -0.70
     neighb
    -0.67
    ravel
    -0.67
     externalToEVAOnly
    -0.66
    icum
    -0.63
    aughtered
    -0.63
    atom
    -0.63
    ULTS
    -0.62
    aced
    -0.62
    POSITIVE LOGITS
    books
    1.20
    book
    1.11
    ably
    1.06
    BOOK
    1.00
     caveats
    0.73
     how
    0.72
     Finder
    0.71
     note
    0.70
    ional
    0.68
    ually
    0.67
    Activations Density 0.024%

    No Known Activations