© 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 EvalsExportsinterp-engineNEWAPI 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. 20691
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a degree of something, especially used in a figurative sense

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ambiguity or uncertainty

    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
    RAW
    -0.83
    absolutely
    -0.82
    ALLY
    -0.80
     absolutely
    -0.75
     Truly
    -0.73
    =>
    -0.72
    enza
    -0.71
    NYSE
    -0.69
    iless
    -0.69
     Absolutely
    -0.69
    POSITIVE LOGITS
     tease
    0.94
     mystery
    0.94
     nuisance
    0.88
     novelty
    0.86
     hassle
    0.86
     gamble
    0.84
     stretch
    0.84
     taboo
    0.84
     spoiler
    0.83
     puzzle
    0.79
    Activations Density 0.106%

    No Known Activations