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. 0-RES-JB
    6. 17417
    Prev
    Next
    INDEX
    Explanations

    mentions of snow

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "snow"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orio
    -0.77
    agine
    -0.72
     Organisation
    -0.72
    reon
    -0.72
    rx
    -0.71
    gate
    -0.70
    LB
    -0.69
    erve
    -0.69
     Cell
    -0.68
    ryu
    -0.67
    POSITIVE LOGITS
     snow
    3.61
    Snow
    2.40
     Snow
    2.28
     snowy
    2.16
     rain
    1.74
     skiing
    1.67
     winter
    1.60
     ski
    1.56
     glaciers
    1.54
     ice
    1.53
    Activations Density 0.021%

    No Known Activations