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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 15793
    Prev
    Next
    INDEX
    Explanations

    phrases related to various medical, legal, and other conditions with the suffix "-related."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate correlations or associations between various topics or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IVER
    -0.77
    ample
    -0.75
    ifter
    -0.70
     Muller
    -0.66
    AUT
    -0.66
    ãĤ©
    -0.65
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.65
     XVI
    -0.63
    oise
    -0.63
    ager
    -0.61
    POSITIVE LOGITS
    tenance
    0.98
    related
    0.87
     proble
    0.87
    ativity
    0.81
     newsp
    0.80
    merce
    0.79
    worldly
    0.78
     unrelated
    0.77
     condem
    0.77
    paren
    0.77
    Activations Density 0.011%

    No Known Activations