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. 22980
    Prev
    Next
    INDEX
    Explanations

    references to music artists and their work, specifically in the rap genre

    oai_token-act-pair · gpt-3.5-turbo
    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
     Pathfinder
    -0.95
     Manit
    -0.91
    ARDIS
    -0.90
     scrut
    -0.89
     Weasley
    -0.80
     HMS
    -0.80
    anasia
    -0.78
     manoeuv
    -0.78
    olkien
    -0.77
    uckland
    -0.77
    POSITIVE LOGITS
     rappers
    1.94
     rapper
    1.91
     Eminem
    1.82
     Kanye
    1.77
     Kendrick
    1.52
     Beyon
    1.49
     DJ
    1.49
     rap
    1.44
     Rih
    1.41
     Hip
    1.40
    Activations Density 0.408%

    No Known Activations