© 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. 4-RES-JB
    11. 14942
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of something being in the middle or halfway through

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with various types of intervals or measurements

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

    No Comments

    Negative Logits
     Wikipedia
    -0.72
    zona
    -0.69
    =-=-=-=-
    -0.68
     QR
    -0.62
    PLA
    -0.62
     Mens
    -0.62
    é»Ĵ
    -0.62
    ipedia
    -0.60
     refere
    -0.59
    SCP
    -0.58
    POSITIVE LOGITS
    endment
    0.85
    imester
    0.78
    ixties
    0.74
    liction
    0.73
    session
    0.72
    Angelo
    0.70
    reet
    0.68
    Enlarge
    0.68
    roxy
    0.67
    spection
    0.67
    Activations Density 0.043%

    No Known Activations