© 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. 0-RES-JB
    11. 8180
    Prev
    Next
    INDEX
    Explanations

    phrases related to surveillance or eavesdropping

    oai_token-act-pair · gpt-3.5-turbo

    terms related to surveillance and monitoring activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prayers
    -0.71
     oil
    -0.65
     glossy
    -0.64
     naming
    -0.63
     Mahjong
    -0.62
     friendship
    -0.62
     tongues
    -0.61
     tun
    -0.60
     heats
    -0.60
     grill
    -0.60
    POSITIVE LOGITS
    dropping
    2.78
    drop
    2.46
    dro
    2.35
    drops
    1.91
    second
    1.78
    played
    1.50
    seconds
    1.10
    perse
    1.08
    Drop
    1.06
    conscious
    0.95
    Activations Density 0.030%

    No Known Activations