© 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 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. 0-RES-JB
    11. 12934
    Prev
    Next
    INDEX
    Explanations

    the word "ouch"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to discomfort or negative experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jun
    -0.64
     Times
    -0.63
     creatively
    -0.63
     winds
    -0.62
     myth
    -0.60
    Arg
    -0.60
     gener
    -0.60
     creative
    -0.59
     initiation
    -0.59
     Kelly
    -0.59
    POSITIVE LOGITS
    ouch
    4.63
    ouched
    1.86
    ou
    1.20
     Couch
    1.17
    ousse
    1.14
    ouf
    1.10
    ools
    1.03
    arget
    1.02
    ollah
    0.95
    Profile
    0.93
    Activations Density 0.011%

    No Known Activations