© 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 EvalsExportsAPI 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. 0-RES-JB
    11. 9595
    Prev
    Next
    INDEX
    Explanations

    the word "iel" followed by a numerical value of either 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    names or references related to specific individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teeth
    -0.69
     Tant
    -0.68
     tamp
    -0.66
     mitochond
    -0.64
     Westbrook
    -0.63
     cap
    -0.63
     clock
    -0.62
     patches
    -0.61
     rh
    -0.61
     bruising
    -0.61
    POSITIVE LOGITS
    iel
    4.58
    riel
    1.37
    iem
    1.31
    ael
    1.26
    uel
    1.15
    elle
    1.14
    ieg
    1.12
    ien
    1.12
    iom
    1.12
    ieu
    1.07
    Activations Density 0.014%

    No Known Activations