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. 10-RES-JB
    6. 18117
    Prev
    Next
    INDEX
    Explanations

    terms related to specific targeting, such as "target genes," "target demographic," and "target market."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific subjects or groups related to a program or study

    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
    cale
    -0.88
    ledge
    -0.80
    utra
    -0.78
    inness
    -0.77
    arus
    -0.77
    tics
    -0.73
    displayText
    -0.72
    ourning
    -0.72
    osuke
    -0.70
    ynthesis
    -0.70
    POSITIVE LOGITS
     organism
    0.84
     cities
    0.81
     classes
    0.81
     sites
    0.80
     regions
    0.80
     organisms
    0.80
     group
    0.79
     countries
    0.78
     areas
    0.77
     cells
    0.77
    Activations Density 0.284%

    No Known Activations