© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20841
    Prev
    Next
    INDEX
    Explanations

    specific mentions of locations or organizations in official contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /"
    -0.78
    udder
    -0.72
    ?).
    -0.72
    —"
    -0.70
    cum
    -0.70
    ?),
    -0.70
    ="/
    -0.69
    ___
    -0.68
    Adds
    -0.68
    pless
    -0.67
    POSITIVE LOGITS
    resa
    1.08
     importance
    1.00
     integrity
    1.00
     totality
    0.99
     seriousness
    0.98
     utmost
    0.97
     slightest
    0.95
     timing
    0.94
     intention
    0.93
     urgency
    0.93
    Activations Density 0.294%

    No Known Activations