© 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. 3-RES-JB
    11. 18004
    Prev
    Next
    INDEX
    Explanations

    comparisons indicating preference or priority

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases emphasizing the word "than."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enser
    -0.75
    ilic
    -0.73
    Eye
    -0.72
    Winged
    -0.69
    pillar
    -0.68
    EMENT
    -0.67
    legged
    -0.67
    essen
    -0.65
    ALE
    -0.65
     largeDownload
    -0.65
    POSITIVE LOGITS
    atos
    0.78
    atever
    0.75
     usual
    0.70
    acles
    0.69
    adelphia
    0.66
    whel
    0.62
    atches
    0.62
     Kn
    0.61
     anywhere
    0.61
    ancock
    0.60
    Activations Density 0.078%

    No Known Activations