© 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. 13757
    Prev
    Next
    INDEX
    Explanations

    mentions of security personnel and actions in a given context

    oai_token-act-pair · gpt-3.5-turbo

    references to security personnel and related actions

    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
    theless
    -0.82
    cipled
    -0.80
    ufact
    -0.77
    oric
    -0.77
    ced
    -0.75
    arget
    -0.73
    alogy
    -0.73
    sonian
    -0.71
    netflix
    -0.71
    ohydrate
    -0.70
    POSITIVE LOGITS
     guards
    1.04
     personnel
    1.00
     clearance
    0.92
     guard
    0.89
     checkpoints
    0.87
     Patrol
    0.82
     screening
    0.82
     Guard
    0.82
     enforcement
    0.79
     Guards
    0.78
    Activations Density 0.041%

    No Known Activations