© 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. 8-RES-JB
    11. 1022
    Prev
    Next
    INDEX
    Explanations

    phrases related to news headlines, including topics like political activities, medical incidents, criminal actions, and official statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of events or situations involving significant harm or danger

    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
    iton
    -0.65
    в
    -0.63
     ACS
    -0.63
     life
    -0.63
    tons
    -0.62
    hement
    -0.60
    pps
    -0.60
    hest
    -0.58
    д
    -0.58
    ean
    -0.58
    POSITIVE LOGITS
    ccording
    0.77
    EPA
    0.70
    BBC
    0.69
    rouse
    0.65
     Prosecutors
    0.64
    inav
    0.62
    accompan
    0.62
    ³³³³³³³³³³³³³³³³
    0.60
    Prosecut
    0.60
     prosecutor
    0.59
    Activations Density 0.131%

    No Known Activations