© 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. 10-RES-JB
    11. 6126
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases related to dates and events

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation, particularly periods and question marks, indicating the conclusion of thoughts or statements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tons
    -0.77
    intention
    -0.71
    worms
    -0.71
    ²¾
    -0.71
    olean
    -0.70
     intending
    -0.70
     microsc
    -0.69
     ordinarily
    -0.65
     computing
    -0.64
    ciplinary
    -0.63
    POSITIVE LOGITS
     Caption
    1.16
     Subscribe
    1.15
     VIDEOS
    1.14
     REUTERS
    1.11
     Written
    1.05
     Photo
    1.04
     Related
    1.03
     SEE
    1.03
     VIDEO
    1.02
     READ
    1.02
    Activations Density 0.225%

    No Known Activations