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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 19137
    Prev
    Next
    INDEX
    Explanations

    keywords related to fishing

    oai_token-act-pair · gpt-3.5-turbo

    references to fishing activities

    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
    xus
    -0.84
    xual
    -0.81
    gow
    -0.74
    haar
    -0.71
    blance
    -0.71
    eus
    -0.71
    vu
    -0.68
     Twain
    -0.67
    stract
    -0.66
    sure
    -0.65
    POSITIVE LOGITS
     fishing
    1.01
     fisherman
    0.98
     fishermen
    0.91
     rods
    0.87
     boats
    0.86
     spears
    0.82
    glers
    0.82
    bowl
    0.81
     expedition
    0.80
    fish
    0.80
    Activations Density 0.017%

    No Known Activations