© 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. 9-RES-JB
    11. 24116
    Prev
    Next
    INDEX
    Explanations

    phrases related to confrontational or intense interactions

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas and periods

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    assian
    -0.81
    abase
    -0.76
    ledged
    -0.72
    ourse
    -0.72
    VERTISEMENT
    -0.70
     Cosponsors
    -0.69
    inction
    -0.68
    eatures
    -0.67
    iminary
    -0.67
    atively
    -0.66
    POSITIVE LOGITS
     huh
    1.36
     eh
    1.21
     sir
    1.15
     please
    1.13
     yeah
    0.98
     oh
    0.95
     darling
    0.93
     hurry
    0.92
     dude
    0.90
     mate
    0.90
    Activations Density 0.227%

    No Known Activations