© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7572
    Prev
    Next
    INDEX
    Explanations

    references to legal professionals or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of U.S. attorneys and related legal references

    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
    Shape
    -0.67
    tics
    -0.64
    byn
    -0.63
    aspx
    -0.61
    Fra
    -0.61
    ksh
    -0.61
    rang
    -0.61
    rake
    -0.60
    java
    -0.59
    php
    -0.58
    POSITIVE LOGITS
    onnaissance
    0.73
    士
    0.70
     Coliseum
    0.69
    assies
    0.64
    uthor
    0.64
    itent
    0.64
    akeru
    0.63
     Yon
    0.63
    addon
    0.62
     Academy
    0.62
    Activations Density 0.154%

    No Known Activations