© 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. 2543
    Prev
    Next
    INDEX
    Explanations

    technical information related to microwave technology, blood circulation, and bureaucratic processes

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

    conjunctions and their varying contexts in sentences

    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
    EStream
    -1.00
    heid
    -0.80
    SHIP
    -0.78
    ulkan
    -0.78
    abwe
    -0.76
     srf
    -0.75
    idth
    -0.75
    rongh
    -0.73
    ipl
    -0.73
    asia
    -0.73
    POSITIVE LOGITS
     unpredictable
    0.97
     predictable
    0.92
     therefore
    0.89
     requires
    0.89
     prone
    0.87
     unreliable
    0.87
     cumbersome
    0.87
     irreversible
    0.86
     counterproductive
    0.85
     ineffective
    0.85
    Activations Density 0.183%

    No Known Activations