© 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. 10337
    Prev
    Next
    INDEX
    Explanations

    words related to organic food and cultivation

    oai_token-act-pair · gpt-3.5-turbo

    negations, particularly in relation to conditions or classifications

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     Jackets
    -0.86
     Slave
    -0.76
     Jericho
    -0.72
     Torrent
    -0.72
     Crawford
    -0.72
     Rings
    -0.72
     Noise
    -0.71
     Bomber
    -0.71
     WTC
    -0.71
     Howe
    -0.70
    POSITIVE LOGITS
    generated
    1.31
    appointed
    1.27
    elected
    1.23
    protected
    1.22
    defined
    1.22
    installed
    1.21
    produced
    1.21
    selected
    1.20
    connected
    1.18
    trained
    1.18
    Activations Density 0.075%

    No Known Activations