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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 13645
    Prev
    Next
    INDEX
    Explanations

    terms related to ice and melting in polar regions

    oai_token-act-pair · gpt-3.5-turbo

    references to ice and its environmental changes

    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
    ãĥ¤
    -0.82
    ilet
    -0.78
    è»
    -0.71
    URA
    -0.69
    hester
    -0.69
    OHN
    -0.69
    eday
    -0.68
     EDITION
    -0.68
    advertising
    -0.68
    ilitary
    -0.67
    POSITIVE LOGITS
     glaciers
    0.95
     lake
    0.89
     accumulation
    0.86
     basin
    0.86
     whales
    0.86
     lakes
    0.84
     iceberg
    0.84
     caves
    0.83
     islands
    0.82
     habitats
    0.82
    Activations Density 0.065%

    No Known Activations