© 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. 9-RES-JB
    11. 11435
    Prev
    Next
    INDEX
    Explanations

    symbols and special characters

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols and emoticons that convey emotion or reactions

    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
    ensibly
    -0.76
     predec
    -0.71
     estranged
    -0.69
     precip
    -0.68
    idium
    -0.66
     shuttle
    -0.66
     inaccur
    -0.65
     emanc
    -0.65
     foreground
    -0.64
     domest
    -0.64
    POSITIVE LOGITS
     Anyway
    1.56
    Anyway
    1.51
    ï¸ı
    1.30
    [/
    1.26
     ;)
    1.26
     :)
    1.23
    ðŁĺ
    1.21
     haha
    1.21
     :(
    1.14
    ;;
    1.13
    Activations Density 0.336%

    No Known Activations