© 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. 3-RES-JB
    11. 17289
    Prev
    Next
    INDEX
    Explanations

    names of famous individuals, like Ashton, Preston, Hastings, and Blackburn

    oai_token-act-pair · gpt-3.5-turbo

    mentions of prominent individuals and their connections

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.87
    opoly
    -0.82
    VERTISEMENT
    -0.80
    ascript
    -0.75
    lda
    -0.73
    ection
    -0.71
    asure
    -0.70
    inatory
    -0.69
    iners
    -0.67
    inals
    -0.66
    POSITIVE LOGITS
     Kut
    1.34
     Ashton
    0.85
    bent
    0.83
     Ratt
    0.78
    rait
    0.76
    raits
    0.72
     buds
    0.69
    hawks
    0.69
    workshop
    0.68
     bent
    0.65
    Activations Density 0.022%

    No Known Activations