© 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. 11505
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    economic issues and crises

    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
     thereof
    -0.73
    omever
    -0.69
     respectively
    -0.63
    oine
    -0.63
     kindly
    -0.61
    ean
    -0.61
    agall
    -0.61
    them
    -0.59
    lication
    -0.59
     ibn
    -0.58
    POSITIVE LOGITS
     looms
    1.11
     threatens
    1.10
     sparks
    1.09
     prompts
    1.05
     Could
    1.01
     hurts
    1.01
     Increases
    0.93
     Causes
    0.93
    ?:
    0.91
     undermines
    0.89
    Activations Density 0.374%

    No Known Activations