© 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. 9-RES-JB
    11. 24064
    Prev
    Next
    INDEX
    Explanations

    discussions about the progress and status of a project

    oai_token-act-pair · gpt-3.5-turbo

    statements about project progress and updates

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     antip
    -0.74
    SPONSORED
    -0.73
    Americans
    -0.70
    heid
    -0.69
    olitics
    -0.69
     outlawed
    -0.68
     Adolf
    -0.68
    gay
    -0.68
     Islamic
    -0.68
     opposes
    -0.66
    POSITIVE LOGITS
     iter
    1.02
    Completed
    0.99
    pleted
    0.96
     backlog
    0.91
     deadlines
    0.91
     finished
    0.87
    ruary
    0.87
     progressed
    0.86
     finalized
    0.86
    months
    0.85
    Activations Density 1.015%

    No Known Activations