© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 17319
    Prev
    Next
    INDEX
    Explanations

    instances of a specific word - "pri"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Cyprus and its governmental or financial issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -1.14
     Leilan
    -0.76
     Hemp
    -0.76
     Everywhere
    -0.73
    ding
    -0.73
     Wink
    -0.71
    schild
    -0.71
     Hurricanes
    -0.70
     Shed
    -0.68
     Wonderland
    -0.65
    POSITIVE LOGITS
    etary
    1.22
    İ
    1.12
    itives
    1.09
    į
    1.07
    Ľ
    1.07
    £
    1.06
    §
    1.06
    ¦
    1.04
    eties
    1.02
    pri
    1.01
    Activations Density 0.007%

    No Known Activations