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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 22293
    Prev
    Next
    INDEX
    Explanations

    words related to sharks

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to sharks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haar
    -0.79
    ijah
    -0.75
    ISTER
    -0.71
     Hemp
    -0.69
    ioch
    -0.68
     Eliot
    -0.68
    olkien
    -0.66
     Fairfax
    -0.66
     Winchester
    -0.66
    Madison
    -0.65
    POSITIVE LOGITS
     fins
    1.07
     reefs
    1.05
     reef
    1.02
    fish
    0.98
     Sharks
    0.92
    ulic
    0.92
     larvae
    0.91
     Reef
    0.87
    arium
    0.85
     aquarium
    0.82
    Activations Density 0.040%

    No Known Activations