Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2573
    Prev
    Next
    INDEX
    Explanations

    phrases associated with the name "Will" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Will from the television show "Will and Grace."

    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
    è¦ļéĨĴ
    -0.89
    advertisement
    -0.74
    cised
    -0.66
    atform
    -0.65
    uctive
    -0.64
    ̶
    -0.63
    anni
    -0.63
    netflix
    -0.62
    catentry
    -0.62
     BIT
    -0.59
    POSITIVE LOGITS
    fulness
    0.71
    brook
    0.69
    ouk
    0.68
    ful
    0.67
     Crom
    0.66
    wagen
    0.65
    nen
    0.65
    WARD
    0.64
     unwitting
    0.64
    cliffe
    0.63
    Activations Density 0.170%

    No Known Activations