© 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. 8-RES-JB
    11. 4141
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yip
    -0.95
    urn
    -0.91
    cair
    -0.85
    thur
    -0.85
    isted
    -0.81
    ranged
    -0.80
    isting
    -0.77
    onement
    -0.76
    lag
    -0.74
    eem
    -0.74
    POSITIVE LOGITS
     agencies
    1.43
     officers
    1.22
     personnel
    1.22
     officials
    1.17
     officer
    1.11
     agency
    1.10
     authorities
    1.08
     agents
    1.04
     establishments
    0.96
     professionals
    0.95
    Activations Density 0.051%

    No Known Activations