© 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. 11-RES-JB
    11. 12730
    Prev
    Next
    INDEX
    Explanations

    words related to technology and specific entities such as names and companies

    oai_token-act-pair · gpt-3.5-turbo

    elements related to proper nouns and names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cole
    -1.20
     Cole
    -1.14
     Lep
    -1.10
    LC
    -0.99
    Luc
    -0.98
    CC
    -0.94
    Lu
    -0.89
    DL
    -0.88
    cell
    -0.87
    Collins
    -0.87
    POSITIVE LOGITS
     Hok
    0.85
    abo
    0.79
    obb
    0.77
    steen
    0.77
    oys
    0.74
    ohan
    0.73
    anky
    0.72
     tatt
    0.72
    OTT
    0.71
    =-=-
    0.70
    Activations Density 0.731%

    No Known Activations