© 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. 12-RES-JB
    11. 4542
    Prev
    Next
    INDEX
    Explanations

    names or titles related to political figures or activists

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of leadership and authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Wilmington
    -0.80
     Titanic
    -0.68
     Colossus
    -0.66
     snag
    -0.60
     chambers
    -0.60
    Columb
    -0.59
     Brenda
    -0.59
     helic
    -0.58
     pregn
    -0.57
     SPD
    -0.57
    POSITIVE LOGITS
    uddin
    1.58
    ullah
    1.46
    zai
    1.38
     Hussain
    1.35
    allah
    1.35
    ollah
    1.32
     Ahmed
    1.31
    awi
    1.30
     Mahm
    1.30
     Sheikh
    1.29
    Activations Density 0.301%

    No Known Activations