© 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. 16749
    Prev
    Next
    INDEX
    Explanations

    mentions of scientists in articles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of scientists or references to science-related topics

    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
     Tactics
    -0.77
     Territories
    -0.71
    BuyableInstoreAndOnline
    -0.71
    teen
    -0.69
     Yanuk
    -0.66
    AAAA
    -0.66
     Ukrain
    -0.66
    loaded
    -0.63
     Dome
    -0.62
    Enough
    -0.59
    POSITIVE LOGITS
     scientist
    0.99
    sonian
    0.92
     studying
    0.91
    ynthesis
    0.88
    ynt
    0.84
     researcher
    0.83
     scientists
    0.80
     physicist
    0.79
    hran
    0.77
    paces
    0.77
    Activations Density 0.033%

    No Known Activations