© 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. 21501
    Prev
    Next
    INDEX
    Explanations

    specific dates and numerical information

    oai_token-act-pair · gpt-3.5-turbo

    elements related to storytelling or narratives

    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
    glers
    -0.72
    rums
    -0.66
    gers
    -0.64
    vier
    -0.63
    udder
    -0.61
    anooga
    -0.59
    obos
    -0.58
    Leaks
    -0.58
    phas
    -0.57
    agog
    -0.57
    POSITIVE LOGITS
     of
    1.30
     OF
    1.10
     Of
    1.08
    of
    0.95
    Of
    0.90
     âĢ
    0.75
    OF
    0.73
    âĢ
    0.73
    !,
    0.69
    ¶
    0.67
    Activations Density 0.767%

    No Known Activations