© 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. 3238
    Prev
    Next
    INDEX
    Explanations

    references to legal and political systems, such as healthcare systems and international alliances

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

    conjunctions and punctuation indicating lists or compound phrases

    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
    displayText
    -0.61
    natureconservancy
    -0.59
    ãĥİ
    -0.58
    umar
    -0.58
    ãĥ£
    -0.58
    DIT
    -0.56
    aclysm
    -0.56
    ective
    -0.55
    ãĤ©
    -0.55
    incible
    -0.55
    POSITIVE LOGITS
     others
    1.32
     countless
    1.08
     even
    1.07
     elsewhere
    1.06
     finally
    1.00
     possibly
    0.98
     assorted
    0.97
     innumerable
    0.97
     many
    0.93
     other
    0.91
    Activations Density 0.172%

    No Known Activations