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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 6572
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions related to 'of course' or 'more importantly'

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating assumptions or qualifications expressed by "of course."

    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
    indal
    -0.79
    ampions
    -0.75
    redients
    -0.71
    ptives
    -0.70
    "],
    -0.66
    iversary
    -0.66
    uties
    -0.64
    eworks
    -0.64
     ];
    -0.64
    aley
    -0.63
    POSITIVE LOGITS
     helicop
    0.70
     Rasm
    0.67
     pse
    0.62
     guessed
    0.61
     fortunately
    0.61
     Leslie
    0.60
    -)
    0.60
     anecd
    0.59
    ĪĴ
    0.57
     preferably
    0.56
    Activations Density 0.294%

    No Known Activations