© 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. 11-RES-JB
    11. 20825
    Prev
    Next
    INDEX
    Explanations

    numbers related to specific events or entities

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers and specific user mentions related to social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.96
    establishment
    -0.83
    elaide
    -0.81
    controlled
    -0.78
    Chel
    -0.77
    centered
    -0.76
    ipl
    -0.75
    amas
    -0.75
    assembled
    -0.75
    osc
    -0.74
    POSITIVE LOGITS
     Alright
    1.43
     Nope
    1.38
     Hey
    1.32
     Hmm
    1.30
     Yeah
    1.28
     Okay
    1.28
     Wow
    1.27
     Quote
    1.27
     Speaking
    1.27
     Looks
    1.27
    Activations Density 0.207%

    No Known Activations