© 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. 3-RES-JB
    11. 15082
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement and police activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of police and law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chery
    -0.81
    oscope
    -0.72
    osphere
    -0.70
    crop
    -0.69
    opian
    -0.69
     perfect
    -0.67
    born
    -0.64
    ocratic
    -0.63
    ãĤ¦
    -0.62
    vote
    -0.61
    POSITIVE LOGITS
     Commissioner
    0.85
     Sources
    0.79
     Reporter
    0.78
     Information
    0.77
     Files
    0.77
     Constable
    0.76
     Officials
    0.76
     Procedures
    0.74
     Superintendent
    0.74
     Dept
    0.73
    Activations Density 0.058%

    No Known Activations