© 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. 2208
    Prev
    Next
    INDEX
    Explanations

    the word "Mon" followed by a single character

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "Mon" or related abbreviations

    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
    gru
    -0.79
    inventoryQuantity
    -0.78
    ingly
    -0.74
    cffffcc
    -0.70
    acks
    -0.68
     cooker
    -0.66
    poke
    -0.65
    acker
    -0.64
    EV
    -0.62
    OIL
    -0.62
    POSITIVE LOGITS
     Mon
    3.74
    Mon
    2.50
     Tue
    1.98
     mon
    1.90
     MON
    1.86
    mon
    1.81
     Fri
    1.71
     Thu
    1.68
     Mono
    1.58
     Wed
    1.51
    Activations Density 0.014%

    No Known Activations