© 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. 0-RES-JB
    11. 16331
    Prev
    Next
    INDEX
    Explanations

    information related to someone leaving or being replaced by another person or entity

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to personality traits, particularly sociability and friendliness

    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
     Legion
    -0.65
    opp
    -0.64
     pawn
    -0.64
     Swordsman
    -0.62
    itcher
    -0.61
     hostage
    -0.61
    hatt
    -0.60
    men
    -0.60
    ront
    -0.60
    peg
    -0.59
    POSITIVE LOGITS
     {\
    2.75
     outgoing
    2.54
     energetic
    1.06
    {\
    1.02
     gir
    0.91
     cheerful
    0.83
    ective
    0.81
    aceous
    0.79
    omers
    0.77
     bil
    0.77
    Activations Density 0.030%

    No Known Activations