Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10976
    Prev
    Next
    INDEX
    Explanations

    terms related to law enforcement and regulations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Columb
    -0.74
    ranged
    -0.68
    ç
    -0.68
    mers
    -0.67
    entary
    -0.67
    iewicz
    -0.66
    ami
    -0.66
    asus
    -0.65
    shape
    -0.65
    cule
    -0.64
    POSITIVE LOGITS
     enforcement
    1.14
     Enforcement
    1.02
     crackdown
    0.95
     sanction
    0.93
     agencies
    0.92
     agency
    0.88
     mechanisms
    0.85
     apparatus
    0.82
    enforcement
    0.81
     policies
    0.80
    Activations Density 0.017%

    No Known Activations