© 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. 11328
    Prev
    Next
    INDEX
    Explanations

    web-related terms like "photo," "Website," or "Twitter," as well as action-inviting terms like "View" or "Sample."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to web content or online resources

    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
    Ħ¢
    -0.71
    angan
    -0.67
    ufact
    -0.67
    mort
    -0.66
     ignition
    -0.64
    ̶
    -0.63
     Gott
    -0.60
    etz
    -0.59
    rehend
    -0.58
     yarn
    -0.55
    POSITIVE LOGITS
    arger
    0.77
    paren
    0.70
    ideos
    0.66
    âĶĢâĶĢâĶĢâĶĢ
    0.66
     Contents
    0.65
    interstitial
    0.64
     Trailer
    0.63
    below
    0.62
    soDeliveryDate
    0.61
    Interstitial
    0.61
    Activations Density 0.102%

    No Known Activations