© 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. 12-RES-JB
    11. 2371
    Prev
    Next
    INDEX
    Explanations

    technical terms related to virtual machines and computer memory management

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    statements related to technology and digital innovation in design processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     exting
    -0.68
    His
    -0.68
    incial
    -0.67
    regon
    -0.65
    ocaust
    -0.64
    Keefe
    -0.64
    aughter
    -0.64
    SPONSORED
    -0.64
    igun
    -0.63
    avior
    -0.63
    POSITIVE LOGITS
     Microsoft
    0.87
     frameworks
    0.85
     optimizing
    0.85
     developers
    0.85
     Adobe
    0.85
     integrating
    0.84
     browsers
    0.83
     startups
    0.83
     enterprises
    0.83
     companies
    0.80
    Activations Density 0.676%

    No Known Activations