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. 5-RES-JB
    6. 2906
    Prev
    Next
    INDEX
    Explanations

    various types of clothing accessories like hats and ties, with a focus on bows

    oai_token-act-pair · gpt-3.5-turbo

    references to "bow" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.76
    },{"
    -0.75
    ochemical
    -0.71
     Mayhem
    -0.70
     Inqu
    -0.70
     Beir
    -0.69
    Downloadha
    -0.69
     Shutterstock
    -0.68
    olutions
    -0.66
    ĸļ
    -0.66
    POSITIVE LOGITS
    bows
    1.05
    strings
    1.04
    bow
    1.04
    els
    1.03
     bow
    0.98
    string
    0.97
     arrow
    0.96
    tie
    0.95
    wright
    0.92
    ler
    0.91
    Activations Density 0.013%

    No Known Activations