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. 9-RES-JB
    6. 8257
    Prev
    Next
    INDEX
    Explanations

    mentions or references to various fishing activities and related scenarios

    oai_token-act-pair · gpt-3.5-turbo

    references to fishing activities and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.99
    mble
    -0.79
    haar
    -0.67
    oppable
    -0.67
     Machina
    -0.64
    xus
    -0.63
    Madison
    -0.62
    ifice
    -0.62
    eanor
    -0.62
    iop
    -0.62
    POSITIVE LOGITS
     fisherman
    1.17
     fishermen
    1.09
     fishing
    1.01
    tailed
    0.99
    fish
    0.97
     boats
    0.92
    tail
    0.92
     fisheries
    0.89
     fish
    0.87
    mong
    0.87
    Activations Density 0.039%

    No Known Activations