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. 0-RES-JB
    6. 14636
    Prev
    Next
    INDEX
    Explanations

    mentions of the musical artist "Drake"

    oai_token-act-pair · gpt-3.5-turbo

    references to the artist Drake

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suff
    -0.71
     ply
    -0.70
     paran
    -0.69
     Kuala
    -0.68
     Euph
    -0.67
    Med
    -0.66
    Condition
    -0.66
     è£ıç
    -0.66
     Relief
    -0.63
     absentee
    -0.63
    POSITIVE LOGITS
     Drake
    3.68
    rake
    1.37
    dra
    1.35
     Nolan
    1.16
     Uncharted
    1.13
     Dre
    1.07
    ozy
    1.02
     Leviathan
    1.01
     Kane
    0.98
     Duke
    0.96
    Activations Density 0.017%

    No Known Activations