© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15811
    Prev
    Next
    INDEX
    Explanations

    words related to causality, particularly indicating what propels or triggers certain actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate causation or influence

    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
    IFT
    -0.69
    urai
    -0.66
     Blackwell
    -0.58
    bral
    -0.56
     Kinnikuman
    -0.56
    oos
    -0.55
    çĦ
    -0.55
     Haku
    -0.54
    ift
    -0.54
     Recon
    -0.54
    POSITIVE LOGITS
     by
    1.39
    by
    1.27
    By
    1.04
     BY
    0.97
     By
    0.94
     partly
    0.92
     principally
    0.92
    BY
    0.89
     chiefly
    0.86
     solely
    0.85
    Activations Density 0.209%

    No Known Activations