© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20886
    Prev
    Next
    INDEX
    Explanations

    the letters "ch" followed by a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ch" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    INGTON
    -0.67
     Circus
    -0.62
     federation
    -0.57
     Ajax
    -0.56
     Independence
    -0.56
     visionary
    -0.56
     Progress
    -0.55
     beyond
    -0.55
    NEY
    -0.55
     Dear
    -0.55
    POSITIVE LOGITS
    ocobo
    1.30
    inese
    1.30
    akra
    1.29
    icago
    1.27
    isel
    1.27
    ieft
    1.26
    ipping
    1.25
    ivalry
    1.23
    attering
    1.23
    ipped
    1.22
    Activations Density 0.014%

    No Known Activations