© 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 EvalsExportsinterp-engineNEWAPI 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. 23481
    Prev
    Next
    INDEX
    Explanations

    words related to emphasis or significance

    oai_token-act-pair · gpt-3.5-turbo

    the word "even" in various contexts

    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
    rend
    -0.86
    HCR
    -0.71
    ected
    -0.71
    utra
    -0.68
    ync
    -0.67
    reating
    -0.64
    ux
    -0.62
    ãĤº
    -0.61
    ugal
    -0.61
    rupt
    -0.60
    POSITIVE LOGITS
    handed
    1.03
     though
    0.96
    handedly
    0.93
     tho
    0.92
     remotely
    0.88
    iates
    0.71
    ivari
    0.70
     mildly
    0.70
     if
    0.69
    parts
    0.67
    Activations Density 0.049%

    No Known Activations