© 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. 10-RES-JB
    11. 6885
    Prev
    Next
    INDEX
    Explanations

    important events or occurrences that hold significance in terms of impact or scale

    oai_token-act-pair · gpt-3.5-turbo

    significant events or crises, particularly relating to attacks or emergencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unts
    -0.66
    tiny
    -0.62
    ruciating
    -0.62
    inate
    -0.61
     resid
    -0.59
    iland
    -0.57
     Subst
    -0.56
    iverse
    -0.56
    kas
    -0.56
    ãĤ¦ãĤ¹
    -0.56
    POSITIVE LOGITS
     ever
    1.28
     EVER
    1.15
     imaginable
    1.09
    ever
    1.04
     since
    0.95
    Ever
    0.90
     Ever
    0.87
     undertaken
    0.82
     anywhere
    0.75
     involving
    0.73
    Activations Density 0.154%

    No Known Activations