© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 21704
    Prev
    Next
    INDEX
    Explanations

    phrases that identify sources of information or quotations

    oai_token-act-pair · gpt-3.5-turbo

    citations or references to media entities, particularly news outlets

    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
    naire
    -0.86
    icion
    -0.72
    TeX
    -0.72
     ILCS
    -0.69
     yen
    -0.68
    BSD
    -0.68
    idas
    -0.67
    Magikarp
    -0.66
    acco
    -0.65
     adolesc
    -0.63
    POSITIVE LOGITS
     Morning
    1.00
    Morning
    0.93
     Situation
    0.90
     Martha
    0.89
     Rachel
    0.89
     MSNBC
    0.85
     Meet
    0.83
     Fare
    0.81
     Today
    0.81
     TODAY
    0.81
    Activations Density 0.064%

    No Known Activations