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

    Neuronpedia

    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. 8-RES-JB
    11. 7837
    Prev
    Next
    INDEX
    Explanations

    references to severe weather conditions or natural disasters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to severe weather events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocre
    -0.69
    orb
    -0.64
    é¾
    -0.64
    DNA
    -0.64
    cheat
    -0.64
    olicited
    -0.63
    creen
    -0.63
    GoldMagikarp
    -0.63
    ingu
    -0.62
    osher
    -0.61
    POSITIVE LOGITS
    ts
    1.50
    tes
    1.19
    ting
    1.19
    ted
    1.17
    te
    1.16
    ters
    1.05
    tted
    1.04
    ments
    0.97
    tic
    0.94
    ter
    0.93
    Activations Density 0.315%

    No Known Activations