© 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. 12212
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical attributes or characteristics of objects

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of objects or entities with specific characteristics

    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
    tests
    -0.92
    ousands
    -0.89
     Cosponsors
    -0.88
    sites
    -0.87
    gements
    -0.87
    testers
    -0.87
    events
    -0.87
     Statements
    -0.86
    ¿
    -0.85
    Days
    -0.84
    POSITIVE LOGITS
     hybrid
    1.06
     whose
    1.06
     consisting
    1.02
     resembling
    0.98
     reminiscent
    0.96
     variant
    0.94
     clone
    0.94
     derivative
    0.89
     designed
    0.89
     affair
    0.89
    Activations Density 0.408%

    No Known Activations