© 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. 22679
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical quantities and statistics

    oai_token-act-pair · gpt-3.5-turbo

    statistics or data related to mortality and health crises

    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
     Tycoon
    -0.60
     Plans
    -0.59
    uart
    -0.56
    chell
    -0.54
     Gould
    -0.53
    igree
    -0.53
    qv
    -0.53
    raints
    -0.52
     Khan
    -0.52
    uve
    -0.52
    POSITIVE LOGITS
     every
    1.96
     annually
    1.76
     daily
    1.70
     yearly
    1.68
    every
    1.66
     weekly
    1.61
     each
    1.57
     everyday
    1.54
    Every
    1.53
     nightly
    1.52
    Activations Density 1.385%

    No Known Activations