© 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. 10-RES-JB
    11. 880
    Prev
    Next
    INDEX
    Explanations

    words related to legal or law enforcement terms, specifically the word 'polic'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal positions or titles, particularly focusing on "Solicitor."

    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
     Chatt
    -0.66
    Gs
    -0.63
     Dresden
    -0.62
     Werewolf
    -0.62
    lessly
    -0.61
    vana
    -0.60
     Rapp
    -0.59
    RF
    -0.56
     Gone
    -0.56
     Breach
    -0.56
    POSITIVE LOGITS
    ious
    1.04
    eous
    0.99
    ies
    0.98
    emen
    0.95
    icals
    0.95
    itor
    0.94
    ciating
    0.92
    ical
    0.91
    sylvania
    0.90
    eman
    0.89
    Activations Density 0.069%

    No Known Activations