© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 9252
    Prev
    Next
    INDEX
    Explanations

    numerical values and math-related words

    oai_token-act-pair · gpt-3.5-turbo

    discussions of statistical likelihoods or uncertainties related to historical or scientific claims

    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
    Effective
    -0.82
    agements
    -0.80
     Achieve
    -0.77
    ourses
    -0.73
    Freedom
    -0.71
    oliberal
    -0.70
    Serv
    -0.69
     Priority
    -0.69
    Interstitial
    -0.69
     Virtue
    -0.68
    POSITIVE LOGITS
     circumst
    1.46
     conjecture
    1.37
     theories
    1.37
     hypothesis
    1.30
     theor
    1.28
     hypotheses
    1.26
     speculate
    1.25
     speculation
    1.24
     conject
    1.23
     speculated
    1.22
    Activations Density 1.037%

    No Known Activations