© 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. 6-RES-JB
    11. 10893
    Prev
    Next
    INDEX
    Explanations

    health-related risk factors and their potential consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health risks and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.63
     Britann
    -0.62
    athi
    -0.61
    vd
    -0.60
     rusty
    -0.58
    olls
    -0.57
     Samar
    -0.57
     repealed
    -0.57
    ãĥ£
    -0.56
     Nielsen
    -0.55
    POSITIVE LOGITS
     purposes
    0.72
     worthwhile
    0.70
     payoff
    0.70
     desired
    0.69
    eering
    0.69
     quicker
    0.65
     desirable
    0.65
    mentation
    0.65
     regardless
    0.65
     lasting
    0.63
    Activations Density 0.784%

    No Known Activations