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. 10-RES-JB
    6. 14508
    Prev
    Next
    INDEX
    Explanations

    words related to communication with emphasis or affirmation

    oai_token-act-pair · gpt-3.5-turbo

    conversational phrases that express humor or sarcasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pires
    -0.73
    minster
    -0.66
    Interestingly
    -0.63
    ³
    -0.62
    abase
    -0.61
    Hack
    -0.60
    Result
    -0.60
    aneous
    -0.60
    lier
    -0.59
    Page
    -0.59
    POSITIVE LOGITS
     please
    1.02
    _-
    1.00
     lest
    1.00
     unless
    0.99
     because
    0.89
    unless
    0.87
     they
    0.84
     it
    0.83
     we
    0.83
     otherwise
    0.82
    Activations Density 0.267%

    No Known Activations