© 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. 1-RES-JB
    11. 14573
    Prev
    Next
    INDEX
    Explanations

    names containing the syllable "ka"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Katrina" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    advertisement
    -0.67
     quot
    -0.64
    quickShipAvailable
    -0.62
     Tillerson
    -0.61
    IDENT
    -0.61
    limits
    -0.61
    ãĥ¼ãĥ³
    -0.61
    Interstitial
    -0.60
    fiction
    -0.60
    ECT
    -0.59
    POSITIVE LOGITS
    ichi
    1.08
    osta
    0.99
    jac
    0.87
    Ga
    0.87
    prus
    0.85
    iba
    0.80
    ia
    0.80
    esthesia
    0.80
    ovic
    0.79
    ja
    0.79
    Activations Density 0.008%

    No Known Activations