© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1-RES-JB
    11. 20292
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mahatma"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mah."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CLSID
    -0.89
    ACTED
    -0.73
    chnology
    -0.73
    PORT
    -0.72
     lav
    -0.71
    CLUS
    -0.70
     Anaheim
    -0.68
    å§
    -0.66
     Ames
    -0.64
     Gemini
    -0.62
    POSITIVE LOGITS
    itary
    1.16
     Mah
    1.10
    omed
    1.00
    Mah
    0.93
    omon
    0.92
    agar
    0.92
    undai
    0.90
    ibaba
    0.90
    oka
    0.89
    alla
    0.89
    Activations Density 0.004%

    No Known Activations