© 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. 20695
    Prev
    Next
    INDEX
    Explanations

    references to the UK

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific geographic location or cultural context

    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
    Reply
    -0.64
     Rollins
    -0.60
     Bland
    -0.59
     poppy
    -0.57
     contr
    -0.56
     prank
    -0.56
     trace
    -0.56
     sheet
    -0.56
    otle
    -0.55
     Danger
    -0.54
    POSITIVE LOGITS
    ulkan
    1.59
    hov
    1.46
    umar
    1.20
    htar
    1.16
    wu
    1.16
    ovych
    1.10
    nown
    1.08
    uyomi
    1.06
    hari
    1.06
    ileaks
    1.06
    Activations Density 0.034%

    No Known Activations