© 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 EvalsExportsAPI 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. 4-RES-JB
    11. 6978
    Prev
    Next
    INDEX
    Explanations

    references to persons or entities named "PA" that hold various positions

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "PA" which likely indicates a specific organization or entity

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

    No Comments

    Negative Logits
    worms
    -0.82
    naire
    -0.80
    lings
    -0.78
    tie
    -0.77
    worldly
    -0.74
    lasses
    -0.73
    cases
    -0.71
    enegger
    -0.71
    link
    -0.68
    doms
    -0.67
    POSITIVE LOGITS
    UL
    1.04
    PA
    0.95
    IRED
    0.89
    WN
    0.89
    EA
    0.87
     PA
    0.80
    itone
    0.76
    VA
    0.76
    USE
    0.76
    VO
    0.76
    Activations Density 0.006%

    No Known Activations