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

    Neuronpedia

    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. 7-RES-JB
    11. 21804
    Prev
    Next
    INDEX
    Explanations

    expressions of admiration or surprise, typically starting with "Wow"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or amazement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    href
    -0.76
     delinqu
    -0.72
     redress
    -0.68
    uting
    -0.68
     obligated
    -0.67
     externalToEVAOnly
    -0.66
    apers
    -0.65
    ãĥ´
    -0.64
     pige
    -0.63
    rive
    -0.63
    POSITIVE LOGITS
    zers
    1.15
     Wow
    0.94
    wow
    0.91
    orld
    0.88
    pedia
    0.88
     wow
    0.86
    ards
    0.80
    yssey
    0.79
    !,
    0.76
    Wow
    0.75
    Activations Density 0.021%

    No Known Activations