© 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. 0-RES-JB
    11. 15442
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement activities or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of police-related activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     irre
    -0.80
     stal
    -0.72
     favor
    -0.70
     tid
    -0.70
     decl
    -0.69
     expansion
    -0.68
     completion
    -0.66
     tick
    -0.65
     bre
    -0.65
     dry
    -0.64
    POSITIVE LOGITS
    Police
    3.40
    police
    2.72
    Officers
    2.42
    Authorities
    2.27
     Police
    2.24
    Prosecutors
    2.02
    Investigators
    1.99
     police
    1.96
    Prosecut
    1.89
    Detect
    1.85
    Activations Density 0.030%

    No Known Activations