© 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. 4835
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions between entities, potentially related to support or opposition

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    prepositions and phrases indicating distribution or allocation

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    He
    -0.75
     he
    -0.71
     himself
    -0.71
     him
    -0.68
    he
    -0.64
     HIM
    -0.60
    His
    -0.58
    him
    -0.58
     He
    -0.57
    Others
    -0.57
    POSITIVE LOGITS
     its
    1.55
     Its
    1.42
    Its
    1.23
     ITS
    0.91
    its
    0.86
     itself
    0.81
     pione
    0.73
    eatures
    0.72
    ø
    0.72
    č
    0.71
    Activations Density 0.773%

    No Known Activations