© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 1220
    Prev
    Next
    INDEX
    Explanations

    phrases related to investigations or inquiries into various incidents or events

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "investigating" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤª
    -0.72
    âĹ¼
    -0.70
    aez
    -0.67
    hold
    -0.66
    ña
    -0.66
    bows
    -0.66
    eries
    -0.64
    ners
    -0.63
    icio
    -0.62
    -|
    -0.62
    POSITIVE LOGITS
     whether
    0.93
     allegations
    0.93
     alleged
    0.77
     probing
    0.75
     irregularities
    0.75
     incidents
    0.74
     UFOs
    0.74
     wrongdoing
    0.73
     independently
    0.72
     misconduct
    0.71
    Activations Density 0.048%

    No Known Activations