© 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. 7403
    Prev
    Next
    INDEX
    Explanations

    the letter "M" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the letter "M" or entities that start with the letter "M."

    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
    ãĤ¡
    -0.91
    DragonMagazine
    -0.90
     Extras
    -0.74
     yours
    -0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.72
    ãģį
    -0.70
     Bleach
    -0.70
     Beyond
    -0.69
     Eleven
    -0.68
     fashioned
    -0.67
    POSITIVE LOGITS
    akin
    1.08
    occ
    1.05
    ixed
    1.00
    oto
    1.00
    apper
    0.98
    antis
    0.98
    apping
    0.96
    OST
    0.95
    asters
    0.95
    osh
    0.94
    Activations Density 0.026%

    No Known Activations