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. 4-RES-JB
    6. 23918
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dude", with a particular emphasis on the variant "dude" with an activation value of 10

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "dude" and its variations in context

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

    No Comments

    Negative Logits
    atories
    -0.87
     Cosponsors
    -0.80
    ateg
    -0.76
    Integ
    -0.75
    oshenko
    -0.74
    ī
    -0.73
    Disk
    -0.73
    inters
    -0.71
    orius
    -0.70
     rall
    -0.69
    POSITIVE LOGITS
    holes
    0.98
    hole
    0.96
     dude
    0.88
     jeans
    0.79
    ards
    0.78
     Dude
    0.72
     messenger
    0.71
     wink
    0.70
     Wink
    0.69
     dudes
    0.67
    Activations Density 0.019%

    No Known Activations