© 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. 0-RES-JB
    11. 13628
    Prev
    Next
    INDEX
    Explanations

    numbers expressing percentage values

    oai_token-act-pair · gpt-3.5-turbo

    the title of a well-known children's story

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LCS
    -0.80
     Tut
    -0.73
    yt
    -0.70
     Eck
    -0.64
    ©¶æ
    -0.64
    Toy
    -0.62
     Shop
    -0.62
     Macy
    -0.61
    ici
    -0.61
     Carney
    -0.61
    POSITIVE LOGITS
    egal
    0.79
    gap
    0.78
    ENA
    0.73
    udos
    0.72
    patch
    0.70
    ooks
    0.70
    anwhile
    0.69
    reek
    0.68
    cms
    0.67
     hence
    0.67
    Activations Density 0.000%

    No Known Activations