© 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. 16991
    Prev
    Next
    INDEX
    Explanations

    terms related to valuable or historical objects

    oai_token-act-pair · gpt-3.5-turbo

    references to historical or cultural artifacts

    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
    sen
    -0.78
    creen
    -0.75
    yan
    -0.74
    rol
    -0.69
    NN
    -0.67
    ter
    -0.67
    rons
    -0.66
    kers
    -0.66
    olitan
    -0.65
    yon
    -0.64
    POSITIVE LOGITS
    ifacts
    1.21
     artifact
    1.20
     artifacts
    1.20
     arte
    1.19
    artifacts
    1.09
    ibles
    0.87
     relics
    0.87
    ifact
    0.84
    smanship
    0.78
    iques
    0.76
    Activations Density 0.009%

    No Known Activations