Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 5025
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "deer"

    oai_token-act-pair · gpt-3.5-turbo

    references to deer and related wildlife

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

    No Comments

    Negative Logits
    ppard
    -0.73
    uyomi
    -0.70
    ochemical
    -0.68
    acist
    -0.67
     disadvant
    -0.64
    oho
    -0.63
    colo
    -0.63
    arcer
    -0.63
    hran
    -0.63
     Wilkinson
    -0.62
    POSITIVE LOGITS
     deer
    1.01
     carc
    0.92
     herds
    0.87
     hunter
    0.86
     hunters
    0.85
    hunter
    0.84
     beetle
    0.83
     hunting
    0.83
     herd
    0.81
    bats
    0.79
    Activations Density 0.012%

    No Known Activations