© 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. 11-RES-JB
    11. 18657
    Prev
    Next
    INDEX
    Explanations

    entities and names mentioned in a short document

    oai_token-act-pair · gpt-3.5-turbo

    specific references to documents, particularly regarding social or financial details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jen
    -0.88
     Jen
    -0.86
    uter
    -0.85
    iner
    -0.85
    Nap
    -0.83
    enn
    -0.81
     McInt
    -0.79
     Hen
    -0.78
     APR
    -0.78
    Plex
    -0.77
    POSITIVE LOGITS
     Fisher
    0.95
     Hod
    0.81
    ;;
    0.81
     Bod
    0.77
    ali
    0.77
     Carib
    0.77
     Lod
    0.73
     Todd
    0.72
     Hand
    0.71
    Handler
    0.71
    Activations Density 0.656%

    No Known Activations