© 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. 14146
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms or phrases related to consequences and actions

    oai_token-act-pair · gpt-3.5-turbo

    punctuated sentences, particularly those indicating significant events or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Period at the end of sentences about things falling apart or ending.

    Explanation Uploaded by User
    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
     tremend
    -0.81
     nomine
    -0.80
     plaus
    -0.79
     hes
    -0.79
     glim
    -0.79
     carbohyd
    -0.79
     intended
    -0.77
     way
    -0.77
     phenomen
    -0.76
     liking
    -0.76
    POSITIVE LOGITS
     Thousands
    1.38
     Journalists
    1.36
     Roads
    1.36
     Families
    1.36
     Electricity
    1.33
     Prices
    1.33
     Schools
    1.32
     Hundreds
    1.32
     Classes
    1.32
     Taxes
    1.31
    Activations Density 0.372%

    No Known Activations