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. 2-RES-JB
    6. 8793
    Prev
    Next
    INDEX
    Explanations

    references to fish

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "fish."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dear
    -0.67
     condem
    -0.67
    pled
    -0.66
    issued
    -0.65
    itzer
    -0.64
     Ames
    -0.63
     Registrar
    -0.60
    STEM
    -0.59
    FINE
    -0.58
     Chancellor
    -0.57
    POSITIVE LOGITS
    bowl
    1.23
    fish
    1.20
    mong
    1.17
     fish
    1.02
     fishes
    0.98
    Fish
    0.95
     fisherman
    0.90
     fishing
    0.89
     tacos
    0.88
     trout
    0.88
    Activations Density 0.010%

    No Known Activations