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. 9-RES-JB
    6. 11850
    Prev
    Next
    INDEX
    Explanations

    mentions of sea levels

    oai_token-act-pair · gpt-3.5-turbo

    references to sea levels and related environmental concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -0.89
    iaries
    -0.80
    iop
    -0.80
    ividual
    -0.79
    thumbnails
    -0.74
    arantine
    -0.73
    IBLE
    -0.72
    iom
    -0.72
    ilyn
    -0.71
    ÑĮ
    -0.71
    POSITIVE LOGITS
    plane
    1.26
    planes
    1.03
     lions
    0.96
     lion
    0.90
     turtle
    0.86
     ot
    0.86
     cuc
    0.85
     Kraken
    0.83
    fish
    0.83
    front
    0.83
    Activations Density 0.038%

    No Known Activations