© 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. 12285
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement vehicles, specifically patrol cars

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement vehicle 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
    akespeare
    -0.73
    rencies
    -0.72
     inflamm
    -0.70
     Centauri
    -0.69
    generic
    -0.69
    hur
    -0.68
    xual
    -0.67
    akespe
    -0.67
    igmat
    -0.66
    bestos
    -0.65
    POSITIVE LOGITS
     patrol
    1.24
     patrols
    1.14
     patrolling
    1.00
     duty
    0.99
    men
    0.92
     Patrol
    0.91
     officers
    0.90
    man
    0.87
    ants
    0.86
     sergeant
    0.86
    Activations Density 0.042%

    No Known Activations