© 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. 14466
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical terms

    oai_token-act-pair · gpt-3.5-turbo

    negative numerical values and their representations

    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
     lieu
    -0.71
     conclusion
    -0.71
     breed
    -0.71
     organized
    -0.71
     earlier
    -0.70
     premise
    -0.70
     prim
    -0.70
     thrill
    -0.70
     volunt
    -0.70
     developmental
    -0.69
    POSITIVE LOGITS
    300
    1.90
    10000
    1.88
    40
    1.87
    20
    1.86
    150
    1.85
    4000
    1.85
    60
    1.85
    50
    1.83
    100
    1.82
    250
    1.82
    Activations Density 0.181%

    No Known Activations