© 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. 13626
    Prev
    Next
    INDEX
    Explanations

    terms related to exposure to various substances or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exposure to various substances or conditions

    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
    assian
    -0.75
    starter
    -0.72
    notations
    -0.71
    maker
    -0.70
    aldi
    -0.64
    ataka
    -0.64
    illard
    -0.62
    eta
    -0.62
     Jou
    -0.62
    cia
    -0.62
    POSITIVE LOGITS
    ibilities
    0.82
     Exposure
    0.79
     weaknesses
    0.74
     vulnerabilities
    0.72
     flaws
    0.70
     Breach
    0.70
    ibly
    0.69
     exposed
    0.67
     exposure
    0.67
    iltr
    0.67
    Activations Density 0.032%

    No Known Activations