© 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. 3-RES-JB
    11. 16376
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the theme of disappearance, loss, and uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    terms related to disappearances and missing persons cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tiers
    -0.74
    fed
    -0.71
     Jinping
    -0.68
     absorbs
    -0.64
     hemisphere
    -0.64
     pomp
    -0.64
    GY
    -0.63
    unin
    -0.63
    ubs
    -0.61
     gust
    -0.60
    POSITIVE LOGITS
    Missing
    1.06
     unsolved
    1.04
     Missing
    1.03
     Investigators
    0.93
     disappearance
    0.91
     Detective
    0.90
     Detect
    0.88
     Bigfoot
    0.88
     Disapp
    0.86
     Mysteries
    0.85
    Activations Density 0.154%

    No Known Activations