© 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. 0-RES-JB
    11. 6503
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Mohammed."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Mohammed."

    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
    enta
    -0.79
    tier
    -0.65
    buck
    -0.63
    burst
    -0.63
     RH
    -0.63
     DS
    -0.61
     canned
    -0.61
     spaced
    -0.61
     multit
    -0.60
    etitive
    -0.59
    POSITIVE LOGITS
     Mohammed
    3.75
     Mohammad
    2.98
    Moh
    2.59
     Mohamed
    2.47
     Muhammad
    2.32
     Ahmed
    1.81
     Koran
    1.78
     Abdullah
    1.72
     Sheikh
    1.70
     Mahmoud
    1.67
    Activations Density 0.022%

    No Known Activations