© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14403
    Prev
    Next
    INDEX
    Explanations

    strong emotional expressions or emphatic language

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing apathy or indifference

    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
    aten
    -0.69
    CHA
    -0.67
    yrinth
    -0.66
    iba
    -0.65
    Ct
    -0.63
    NING
    -0.62
    ipel
    -0.62
    ADE
    -0.61
    indle
    -0.60
    xtap
    -0.59
    POSITIVE LOGITS
     impression
    0.89
     thumbs
    0.82
     cred
    0.80
    icum
    0.79
     nod
    0.78
     keynote
    0.77
     insight
    0.77
     advice
    0.76
     reins
    0.75
     speeches
    0.75
    Activations Density 0.185%

    No Known Activations