© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 16125
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of surprise

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with surcharges or related financial concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    itsch
    -0.73
    ovie
    -0.70
    icals
    -0.69
    endor
    -0.66
    enburg
    -0.64
    hetti
    -0.63
     Investors
    -0.63
    isner
    -0.63
     Away
    -0.61
    oyd
    -0.60
    POSITIVE LOGITS
     sur
    1.02
    sur
    0.88
    geons
    0.86
    mounted
    0.85
    chal
    0.81
    lation
    0.81
    iors
    0.77
    reys
    0.77
    rir
    0.77
    Creat
    0.77
    Activations Density 0.005%

    No Known Activations