© 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. 7-RES-JB
    11. 22578
    Prev
    Next
    INDEX
    Explanations

    proper nouns of people, places, and brands

    oai_token-act-pair · gpt-3.5-turbo

    the use of possessive forms or a specific structure in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artifacts
    -0.68
    rats
    -0.68
    authors
    -0.66
    arians
    -0.63
    needed
    -0.63
    links
    -0.62
    sudo
    -0.61
     Europeans
    -0.61
    iologist
    -0.60
     retirees
    -0.60
    POSITIVE LOGITS
     inaugural
    0.91
     behalf
    0.90
     own
    0.90
     midst
    0.88
     coffers
    0.83
     darkest
    0.82
     backyard
    0.82
     infancy
    0.81
     doorstep
    0.80
     realm
    0.80
    Activations Density 0.197%

    No Known Activations