© 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. 18814
    Prev
    Next
    INDEX
    Explanations

    exclamations and personal expressions used in conversation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "you are" or its variations

    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
     tension
    -0.72
     blending
    -0.71
     scarcity
    -0.69
     succession
    -0.68
     alternating
    -0.68
     friction
    -0.66
     rotating
    -0.65
     isolation
    -0.65
     delegation
    -0.63
     utilization
    -0.62
    POSITIVE LOGITS
    mite
    1.05
    s
    0.99
    mean
    0.97
    ï¸ı
    0.96
    ng
    0.95
    med
    0.90
    st
    0.90
    t
    0.90
    tain
    0.89
    amaz
    0.88
    Activations Density 0.169%

    No Known Activations