© 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. 8-RES-JB
    11. 7606
    Prev
    Next
    INDEX
    Explanations

    time periods or ranges

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "between" and its variations that indicate ranges or intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGR
    -0.86
    gow
    -0.76
    vous
    -0.74
    rav
    -0.73
    eto
    -0.72
    jew
    -0.68
     unfocusedRange
    -0.65
    atically
    -0.63
    unc
    -0.62
    orth
    -0.62
    POSITIVE LOGITS
     halves
    0.86
     sexes
    0.78
     genders
    0.76
     bouts
    0.70
     extremes
    0.67
     Worlds
    0.66
     rounds
    0.65
    ãĥīãĥ©ãĤ´ãĥ³
    0.64
    stocks
    0.64
     factions
    0.62
    Activations Density 0.043%

    No Known Activations