© 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. 12-RES-JB
    11. 3038
    Prev
    Next
    INDEX
    Explanations

    words related to confusion or surprise

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    expressions of confusion or surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     antioxid
    -0.81
     diam
    -0.72
     bye
    -0.70
     newsp
    -0.66
     Principal
    -0.65
     bearer
    -0.65
     OU
    -0.63
     rough
    -0.61
     federation
    -0.61
     fore
    -0.61
    POSITIVE LOGITS
    lement
    1.22
    ances
    1.07
    enment
    1.06
    rehens
    1.04
    ance
    1.04
    ment
    1.00
    ement
    1.00
    rations
    0.99
    lements
    0.98
    ience
    0.97
    Activations Density 0.047%

    No Known Activations