© 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. 8-RES-JB
    11. 14115
    Prev
    Next
    INDEX
    Explanations

    phrases related to completing or occupying something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to filling gaps or voids

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    rf
    -0.67
    Friends
    -0.64
    nature
    -0.64
    won
    -0.63
    pract
    -0.63
    isation
    -0.62
    aji
    -0.60
    appro
    -0.60
    recogn
    -0.59
    dar
    -0.59
    POSITIVE LOGITS
     vacancies
    1.02
     gaps
    0.99
    ups
    0.85
    ummer
    0.82
     coffers
    0.81
     shortages
    0.79
     shelves
    0.79
     void
    0.79
    oresc
    0.77
     notebooks
    0.77
    Activations Density 0.049%

    No Known Activations