© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 23208
    Prev
    Next
    INDEX
    Explanations

    the term "Cop" or variations related to law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to "Cop" and its variations, likely indicating a focus on law enforcement or police-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.72
    itably
    -0.71
    committee
    -0.69
    avez
    -0.67
    FORE
    -0.66
    veyard
    -0.65
    WAYS
    -0.65
    rely
    -0.65
    imaru
    -0.64
    WAY
    -0.64
    POSITIVE LOGITS
     Cop
    1.28
    Cop
    1.21
    yrights
    1.04
    cop
    0.82
    iago
    0.79
    lete
    0.78
    ulative
    0.78
    eland
    0.77
    icker
    0.74
    rodu
    0.73
    Activations Density 0.005%

    No Known Activations