© 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. 10-RES-JB
    11. 18770
    Prev
    Next
    INDEX
    Explanations

    names of places

    oai_token-act-pair · gpt-3.5-turbo

    specific combinations of letters or syllables that could relate to names or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICLE
    -0.70
    ortment
    -0.61
    htaking
    -0.61
    hole
    -0.57
     necks
    -0.57
    udic
    -0.56
    66666666
    -0.55
     psychiat
    -0.53
     è£ıè
    -0.53
    holes
    -0.51
    POSITIVE LOGITS
    vre
    0.81
    lings
    0.66
    rio
    0.65
    enz
    0.63
    imating
    0.63
    ename
    0.61
    heim
    0.61
    orthy
    0.61
    imate
    0.60
    ibling
    0.59
    Activations Density 0.191%

    No Known Activations