© 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. 7-RES-JB
    11. 14223
    Prev
    Next
    INDEX
    Explanations

    phrases related to business, ownership, and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    references to businesses or companies, particularly in relation to their size or ownership

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ãĥ´ãĤ¡
    -0.75
    ãģı
    -0.72
    qv
    -0.70
     scrut
    -0.69
    ãĤĮ
    -0.68
    ãĥ¼ãĥĨ
    -0.67
     answ
    -0.67
    ãģĻ
    -0.64
    ãģį
    -0.63
     [*
    -0.63
    POSITIVE LOGITS
     awaits
    0.74
     âĵĺ
    0.66
    pires
    0.63
    poses
    0.61
     Belfast
    0.60
     founded
    0.59
     welcomes
    0.58
     celebrates
    0.58
     hailed
    0.57
     Bangkok
    0.57
    Activations Density 0.923%

    No Known Activations