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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 11-RES-JB
    6. 10869
    Prev
    Next
    INDEX
    Explanations

    information related to jellyfish, especially their environmental impact and uses

    oai_token-act-pair · gpt-3.5-turbo

    terms related to jellyfish and their environmental impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    furt
    -0.84
     Kahn
    -0.81
    HUD
    -0.79
    raints
    -0.78
     Pace
    -0.76
     Ticket
    -0.76
     Dealer
    -0.75
     Fargo
    -0.74
     Romo
    -0.74
     Singh
    -0.73
    POSITIVE LOGITS
     algae
    2.21
     coral
    1.86
     reefs
    1.79
     reef
    1.64
     crabs
    1.60
     seaw
    1.60
     marine
    1.53
     organisms
    1.51
     oy
    1.51
     plank
    1.47
    Activations Density 0.148%

    No Known Activations