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. 9-RES-JB
    6. 15322
    Prev
    Next
    INDEX
    Explanations

    direct responses of negation or refusal

    oai_token-act-pair · gpt-3.5-turbo

    negative responses or denials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.72
     reverted
    -0.65
    kefeller
    -0.63
    drawn
    -0.60
    rored
    -0.60
    sing
    -0.58
    pez
    -0.58
    ylan
    -0.57
    riers
    -0.57
    abal
    -0.57
    POSITIVE LOGITS
     sir
    0.96
     Nope
    0.91
    terday
    0.89
    !
    0.88
    !,
    0.83
    !.
    0.83
     Absolutely
    0.79
     worries
    0.78
    !!!!
    0.77
    .
    0.77
    Activations Density 0.072%

    No Known Activations