© 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. 10-RES-JB
    11. 11332
    Prev
    Next
    INDEX
    Explanations

    mentions of personal names, particularly with the letter 'm'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter "m" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pitch
    -0.81
     tip
    -0.71
     foul
    -0.69
    EStream
    -0.67
     tips
    -0.67
     Intercept
    -0.65
     Prompt
    -0.65
     freeze
    -0.62
     shortened
    -0.62
     Mechdragon
    -0.62
    POSITIVE LOGITS
    ichael
    1.54
    agn
    1.37
    otor
    1.36
    ixed
    1.36
    ovies
    1.35
    arijuana
    1.35
    obiles
    1.35
    useum
    1.32
    igration
    1.31
    obil
    1.29
    Activations Density 0.035%

    No Known Activations