© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18493
    Prev
    Next
    INDEX
    Explanations

    references to the word "Shark"

    oai_token-act-pair · gpt-3.5-turbo

    references to sharks and shark-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cussion
    -0.73
    haar
    -0.72
    ISTER
    -0.71
    ISION
    -0.68
     Winchester
    -0.67
    theless
    -0.67
    icably
    -0.65
    mble
    -0.64
     Hemp
    -0.63
    dit
    -0.63
    POSITIVE LOGITS
    ulic
    0.90
    fish
    0.89
    mong
    0.87
     fins
    0.83
    bowl
    0.82
     Sharks
    0.81
     Tank
    0.81
    arium
    0.79
    iasis
    0.77
     Swarm
    0.77
    Activations Density 0.028%

    No Known Activations