© 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. 0-RES-JB
    11. 15289
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mahdi."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Mah" and its variations

    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
     ticks
    -0.79
    FACE
    -0.71
     astronaut
    -0.71
     tick
    -0.69
     XCOM
    -0.68
     drag
    -0.68
     repe
    -0.66
     neurot
    -0.65
     ¯
    -0.65
    aires
    -0.65
    POSITIVE LOGITS
     Mah
    3.79
    Mah
    3.15
     mah
    2.00
     Moh
    1.47
     Bh
    1.37
     Mahm
    1.35
     Mahar
    1.31
     Brah
    1.30
    Moh
    1.26
     Vaj
    1.21
    Activations Density 0.013%

    No Known Activations