© 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. 1943
    Prev
    Next
    INDEX
    Explanations

    words related to determination, evaluation, and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evaluation and assessment processes

    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
    ãĤ´ãĥ³
    -0.90
    amon
    -0.75
    Torrent
    -0.71
    ĸļ
    -0.70
    ãĥ¼ãĤ¯
    -0.67
    ovie
    -0.67
    =]
    -0.66
    ãģĭ
    -0.65
     Ibid
    -0.64
    ographed
    -0.62
    POSITIVE LOGITS
     whether
    1.55
     if
    1.25
    whether
    1.10
     eligibility
    1.07
     how
    1.07
     which
    1.04
     exactly
    0.96
     optimal
    0.95
     what
    0.94
     Whether
    0.89
    Activations Density 0.130%

    No Known Activations