© 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. 1-RES-JB
    11. 24315
    Prev
    Next
    INDEX
    Explanations

    references to snow or winter-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "Snow" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igious
    -0.71
    ect
    -0.69
     Gujar
    -0.65
    ����
    -0.64
    hetical
    -0.63
    izabeth
    -0.62
    ista
    -0.61
    ented
    -0.61
    arians
    -0.61
    arian
    -0.60
    POSITIVE LOGITS
    flake
    1.31
     Snow
    1.15
    Snow
    0.89
     Leopard
    0.86
    storms
    0.85
     mathemat
    0.80
    dale
    0.80
    bats
    0.79
     Crash
    0.79
    tro
    0.79
    Activations Density 0.004%

    No Known Activations