© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11129
    Prev
    Next
    INDEX
    Explanations

    descriptions of events, crimes, accidents, and police activities

    oai_token-act-pair · gpt-3.5-turbo

    key information regarding criminal incidents and law enforcement activities

    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
     neocons
    -0.89
     Authors
    -0.80
    TPP
    -0.73
     Economist
    -0.73
     intellectuals
    -0.73
     Literary
    -0.72
     Philos
    -0.70
    Brexit
    -0.70
    apore
    -0.69
     Tolkien
    -0.69
    POSITIVE LOGITS
     paramedics
    1.23
    ewitness
    1.18
    Investigators
    1.18
     detectives
    1.16
    APD
    1.12
    Police
    1.11
    Officers
    1.10
    police
    1.10
     firefighters
    1.08
     troopers
    1.08
    Activations Density 0.561%

    No Known Activations