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

    Neuronpedia

    Jacobian LensNEW
    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. 8495
    Prev
    Next
    INDEX
    Explanations

    words related to law enforcement personnel and activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of police officers

    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
    Tea
    -0.82
    creen
    -0.80
    ensical
    -0.75
    ilaterally
    -0.74
    dos
    -0.73
    eries
    -0.72
    âĶģ
    -0.72
    icans
    -0.71
     Remastered
    -0.71
    ankind
    -0.71
    POSITIVE LOGITS
     corps
    0.89
     stationed
    0.82
     examiner
    0.82
     officer
    0.82
    utenant
    0.81
    geant
    0.79
     Corps
    0.75
     holster
    0.74
     testified
    0.72
     tasked
    0.72
    Activations Density 0.078%

    No Known Activations