© 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. 6-RES-JB
    11. 13585
    Prev
    Next
    INDEX
    Explanations

    phrases introducing surprising or interesting information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the words "interestingly" and "ironically."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heit
    -0.73
    aily
    -0.71
    "},"
    -0.68
     throats
    -0.66
    ainment
    -0.64
     commitment
    -0.63
     newsletters
    -0.62
    aden
    -0.61
     laundry
    -0.61
    ujah
    -0.60
    POSITIVE LOGITS
    nown
    0.82
     ironically
    0.78
     Ironically
    0.75
     coinc
    0.74
     interestingly
    0.72
     ironic
    0.71
     titled
    0.70
     disposed
    0.70
    SPONSORED
    0.70
     Interestingly
    0.68
    Activations Density 0.054%

    No Known Activations