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. 1-RES-JB
    6. 18342
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Bader."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly surnames and names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transitional
    -0.70
     archived
    -0.70
     archaic
    -0.66
     remote
    -0.66
     subordinate
    -0.63
     historic
    -0.63
     mythical
    -0.61
     recurring
    -0.61
     sacred
    -0.61
     fictional
    -0.60
    POSITIVE LOGITS
    ader
    1.43
    andom
    1.03
    cade
    0.93
    aders
    0.90
    DragonMagazine
    0.88
    artisan
    0.83
    ame
    0.82
    geist
    0.79
    Afee
    0.79
    ragon
    0.78
    Activations Density 0.005%

    No Known Activations