© 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. 2654
    Prev
    Next
    INDEX
    Explanations

    terms related to political or social issues and terms related to money or financial matters

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

    instances of rarity or uniqueness in context

    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
     âĢ
    -0.66
     reluct
    -0.59
     redes
    -0.59
     Euph
    -0.58
     derog
    -0.56
     è£ıç
    -0.55
    ãĥİ
    -0.55
    ãĤº
    -0.55
    Äĩ
    -0.55
    ãĢ
    -0.55
    POSITIVE LOGITS
    itled
    0.58
    he
    0.57
    icent
    0.56
    Guide
    0.54
    om
    0.53
    earth
    0.53
     Life
    0.53
    ome
    0.52
    arate
    0.51
    -
    0.51
    Activations Density 0.366%

    No Known Activations