© 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. 10-RES-JB
    11. 19007
    Prev
    Next
    INDEX
    Explanations

    numeric values related to pricing and valuation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pricing and valuation of items or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.77
    akuya
    -0.72
    court
    -0.71
    warts
    -0.69
    holding
    -0.68
    oker
    -0.67
    flies
    -0.67
    alter
    -0.66
    oho
    -0.66
    luence
    -0.66
    POSITIVE LOGITS
     differently
    1.25
     accordingly
    1.20
     downwards
    1.06
     favorably
    0.97
     appropriately
    0.96
     upwards
    0.95
     upward
    0.91
     incorrectly
    0.91
     correctly
    0.90
     harshly
    0.87
    Activations Density 0.154%

    No Known Activations