© 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. 6-RES-JB
    11. 12037
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement agencies or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to police activity or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vironment
    -0.86
    Leary
    -0.80
    endon
    -0.75
     Lear
    -0.74
     Whitney
    -0.73
    Todd
    -0.71
     Hubbard
    -0.70
    anza
    -0.70
    Hop
    -0.69
     unborn
    -0.69
    POSITIVE LOGITS
     officers
    0.93
     crackdown
    0.93
     raided
    0.90
     officer
    0.83
    orate
    0.81
     tasked
    0.81
     officials
    0.81
     colonel
    0.80
     detained
    0.80
     departments
    0.80
    Activations Density 0.098%

    No Known Activations