© 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. 12506
    Prev
    Next
    INDEX
    Explanations

    references to the name "Chi".

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Greek letter "Chi" and related terms

    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
    ester
    -0.69
     payload
    -0.66
     rem
    -0.65
    \<
    -0.64
    fd
    -0.63
     dred
    -0.61
     overlay
    -0.61
    itement
    -0.60
     Holder
    -0.60
    laden
    -0.60
    POSITIVE LOGITS
     Chi
    4.12
     chi
    2.22
     chirop
    2.02
     Phi
    1.41
     Chun
    1.33
     Chu
    1.31
    chi
    1.28
     Chic
    1.26
     Chong
    1.26
     Ci
    1.23
    Activations Density 0.013%

    No Known Activations