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. 11-RES-JB
    6. 7938
    Prev
    Next
    INDEX
    Explanations

    references to amateur or indie activities, particularly in creative or artistic contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to amateur and indie creators or participants in various artistic fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arching
    -0.84
    oran
    -0.80
    ãħĭ
    -0.76
    aukee
    -0.73
    ysical
    -0.70
    raints
    -0.70
     Cosponsors
    -0.66
    inus
    -0.66
    vic
    -0.64
    atorial
    -0.64
    POSITIVE LOGITS
     adventurer
    0.94
     racer
    0.93
     gamer
    0.88
     filmmaker
    0.86
     fisherman
    0.86
    glers
    0.85
     musician
    0.84
     programmer
    0.84
     hacker
    0.84
     hackers
    0.81
    Activations Density 0.159%

    No Known Activations