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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18330
    Prev
    Next
    INDEX
    Explanations

    contractions and pronouns indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and expressions relating to subjective or personal perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lump
    -0.68
     Peak
    -0.66
     Helm
    -0.65
     Ammunition
    -0.63
     Weight
    -0.62
     Boys
    -0.62
     Option
    -0.62
     Mob
    -0.61
    Interested
    -0.61
     Monthly
    -0.61
    POSITIVE LOGITS
    cause
    0.90
    tis
    0.90
    'll
    0.87
    chy
    0.79
    bsite
    0.78
    arers
    0.78
    pecially
    0.75
    ald
    0.74
    just
    0.74
    ching
    0.73
    Activations Density 0.258%

    No Known Activations