© 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. 8-RES-JB
    11. 24501
    Prev
    Next
    INDEX
    Explanations

    dates or time-related events that mark significant changes or shifts

    oai_token-act-pair · gpt-3.5-turbo

    events or significant changes in history

    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
    cius
    -0.72
     derivative
    -0.66
     overlap
    -0.66
    monary
    -0.66
     actionGroup
    -0.65
     analogous
    -0.65
     similar
    -0.64
     activ
    -0.63
    zai
    -0.63
     scripting
    -0.63
    POSITIVE LOGITS
    ï¸
    0.88
     Melania
    0.83
     Michelle
    0.75
     Lydia
    0.73
    ï¸ı
    0.73
     Coulter
    0.73
     Schumer
    0.72
    PORT
    0.72
     Hann
    0.69
     Karen
    0.66
    Activations Density 0.470%

    No Known Activations