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. 3-RES-JB
    6. 2611
    Prev
    Next
    INDEX
    Explanations

    mentions of specific time periods in the distant past

    oai_token-act-pair · gpt-3.5-turbo

    references to geological time scales, specifically the age of events and formations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.78
    ĪĴ
    -0.76
    iqu
    -0.69
    trak
    -0.65
     practition
    -0.65
     behavi
    -0.65
    vy
    -0.64
    inburgh
    -0.64
    Appearance
    -0.64
    agle
    -0.63
    POSITIVE LOGITS
     ago
    1.30
     Ago
    0.89
     olds
    0.79
     BCE
    0.78
    renheit
    0.75
     apiece
    0.72
     consecut
    0.70
     span
    0.70
    glass
    0.69
    ruary
    0.69
    Activations Density 0.100%

    No Known Activations