© 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. 1-RES-JB
    11. 20493
    Prev
    Next
    INDEX
    Explanations

    words related to chaos, intensity, or drama

    oai_token-act-pair · gpt-3.5-turbo

    words associated with twisted or dark themes, particularly in titles and character names

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    merce
    -0.84
    ð
    -0.83
    OPLE
    -0.80
    inson
    -0.79
    ably
    -0.76
    ffer
    -0.75
    rolet
    -0.75
    VERTISEMENT
    -0.75
    PLIED
    -0.74
    ufact
    -0.74
    POSITIVE LOGITS
     Dreams
    0.99
     Bast
    0.90
     Sister
    0.88
     Lives
    0.87
     Warrior
    0.86
     Eagle
    0.85
     Sisters
    0.85
     Bastard
    0.84
     Masquerade
    0.84
     Heart
    0.84
    Activations Density 0.032%

    No Known Activations