© 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. 18638
    Prev
    Next
    INDEX
    Explanations

    issues or problems and their fixes or corrections within a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bug fixes or corrections in software or articles

    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
    aceae
    -0.77
    DragonMagazine
    -0.74
    erenn
    -0.72
     testament
    -0.71
    女
    -0.71
    apolis
    -0.68
    bard
    -0.67
    STON
    -0.66
    hood
    -0.65
     reckoned
    -0.65
    POSITIVE LOGITS
     incorrectly
    1.36
     improperly
    1.29
     inaccur
    1.27
     faulty
    1.23
     mishand
    1.21
     incorrect
    1.17
     inappropriately
    1.16
     misinterpret
    1.12
     improper
    1.11
     wrongly
    1.11
    Activations Density 1.094%

    No Known Activations