© 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. 7-RES-JB
    11. 20775
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Frost"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to frost and snow, particularly focusing on the word "Frost."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alogue
    -0.73
    perature
    -0.68
    selves
    -0.67
    riage
    -0.63
    ccess
    -0.63
    ister
    -0.62
    assian
    -0.62
     Lumpur
    -0.61
    ention
    -0.61
    plete
    -0.60
    POSITIVE LOGITS
    bite
    1.39
    enstein
    0.95
    flake
    0.91
    burn
    0.82
    fell
    0.80
    wolves
    0.80
    gren
    0.79
    cream
    0.79
    tro
    0.78
    fur
    0.78
    Activations Density 0.033%

    No Known Activations