© 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. 13832
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Mah"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mah."

    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
    chnology
    -0.74
     unquestion
    -0.68
     Albion
    -0.62
     opposite
    -0.60
    TION
    -0.60
     correct
    -0.60
     redistributed
    -0.59
    intendent
    -0.58
     hint
    -0.57
     resulting
    -0.57
    POSITIVE LOGITS
    bub
    1.20
    alo
    1.12
    omed
    1.09
    oning
    1.08
    omet
    1.08
    oney
    1.07
    ony
    1.05
    jong
    1.05
    omes
    1.05
    alla
    0.98
    Activations Density 0.027%

    No Known Activations