© 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. 17429
    Prev
    Next
    INDEX
    Explanations

    words related to news articles or headlines

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "news" in various contexts

    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
    istically
    -0.72
    uras
    -0.70
    istic
    -0.66
     goodwill
    -0.65
     Luther
    -0.62
     rapists
    -0.61
    sighted
    -0.61
     bike
    -0.59
     lubric
    -0.58
     rapist
    -0.58
    POSITIVE LOGITS
    chool
    0.99
    ashington
    0.94
    atcher
    0.93
    ystem
    0.93
    hower
    0.92
    åº
    0.91
    ource
    0.90
    ynski
    0.87
    peed
    0.87
    linger
    0.82
    Activations Density 0.012%

    No Known Activations