© 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. 12911
    Prev
    Next
    INDEX
    Explanations

    research organizations and institutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating collaborations or partnerships among organizations

    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
    ettings
    -0.77
    perfect
    -0.74
    etting
    -0.74
    always
    -0.73
    inct
    -0.72
    bending
    -0.72
    imens
    -0.69
    cells
    -0.66
    pleasant
    -0.66
    activity
    -0.66
    POSITIVE LOGITS
     others
    0.99
     affiliated
    0.93
     elsewhere
    0.87
     Thomson
    0.86
     Friends
    0.84
     ITS
    0.84
     Nex
    0.84
     Sons
    0.81
    ortium
    0.81
     Univ
    0.81
    Activations Density 0.221%

    No Known Activations