© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 4090
    Prev
    Next
    INDEX
    Explanations

    proper nouns and other specific terms, likely related to news topics or titles

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to ratings, reviews, and financial metrics

    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
     Ily
    -0.71
    baugh
    -0.67
     RF
    -0.67
     spir
    -0.64
     Painter
    -0.63
     flared
    -0.63
     marching
    -0.62
     interrupted
    -0.61
     Tib
    -0.61
     seeded
    -0.60
    POSITIVE LOGITS
    Review
    2.93
    Rat
    2.65
    Submit
    1.39
    Rating
    1.39
    Score
    1.30
    Pros
    1.23
    Year
    1.22
    Rate
    1.17
    Frames
    1.16
    Rum
    1.14
    Activations Density 0.064%

    No Known Activations