© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4746
    Prev
    Next
    INDEX
    Explanations

    references to international organizations or entities with the word "Inter" in their name

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

    occurrences of the prefix "Inter," indicating a focus on international topics or entities

    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
     deduction
    -0.61
     Rumble
    -0.61
     bump
    -0.60
     outside
    -0.58
     boo
    -0.58
     exerc
    -0.58
     THREE
    -0.58
     around
    -0.57
     TWO
    -0.57
     Clarkson
    -0.57
    POSITIVE LOGITS
    governmental
    1.48
    agency
    1.31
    disciplinary
    1.19
    faith
    1.16
    continental
    1.13
    Contin
    1.01
    cultural
    1.01
    gener
    1.01
    trop
    0.99
    dimensional
    0.96
    Activations Density 0.016%

    No Known Activations