© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20676
    Prev
    Next
    INDEX
    Explanations

    highlights or key points in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to activities, events, or actions that indicate engagement or participation

    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
    ãĥ¼ãĥ
    -0.73
    apest
    -0.73
    ãĥĻ
    -0.70
    ioxide
    -0.69
    utable
    -0.68
    ãĥĩãĤ£
    -0.68
    оÐ
    -0.68
    ãĥĥãĥī
    -0.67
    Ľ
    -0.66
    abling
    -0.66
    POSITIVE LOGITS
     during
    1.24
     for
    1.20
     with
    1.15
     without
    1.00
     against
    0.98
     throughout
    0.98
     in
    0.98
     alongside
    0.98
     before
    0.97
     after
    0.95
    Activations Density 0.736%

    No Known Activations