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. 8606
    Prev
    Next
    INDEX
    Explanations

    amateur-related terms or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of amateur activities or roles

    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
    pring
    -0.83
    itol
    -0.82
     Gates
    -0.78
     (%
    -0.73
     Morph
    -0.68
     Sessions
    -0.65
    llor
    -0.65
     Pik
    -0.64
     Migration
    -0.63
     Voting
    -0.63
    POSITIVE LOGITS
     amateur
    3.73
     Amateur
    3.02
    ateur
    2.48
    ateurs
    2.44
     novice
    1.45
     collegiate
    1.38
     professional
    1.37
    professional
    1.32
     beginner
    1.29
     hobby
    1.25
    Activations Density 0.018%

    No Known Activations