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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 10595
    Prev
    Next
    INDEX
    Explanations

    references to lotteries or lots of land

    oai_token-act-pair · gpt-3.5-turbo

    references to "lot" and related terms indicating quantity or groupings

    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
    zyk
    -0.66
     Advocate
    -0.64
     Prohibition
    -0.63
     cogn
    -0.62
     Channel
    -0.62
     Revolutionary
    -0.61
     privileged
    -0.61
    âĻ¦
    -0.61
     Airl
    -0.60
     Nich
    -0.60
    POSITIVE LOGITS
    tery
    1.62
    ter
    1.17
    uses
    0.97
    ions
    0.94
    lins
    0.90
    ortment
    0.87
    us
    0.87
    oys
    0.86
    stones
    0.86
    ioned
    0.84
    Activations Density 0.039%

    No Known Activations