© 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. 4-RES-JB
    11. 16081
    Prev
    Next
    INDEX
    Explanations

    mentions of the quantity "six" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the number six in various contexts

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

    No Comments

    Negative Logits
    lance
    -0.74
    itionally
    -0.67
    rade
    -0.64
    ensional
    -0.63
    Ñĭ
    -0.63
    hra
    -0.61
    IAS
    -0.61
    itivity
    -0.60
    iah
    -0.59
    ÃĥÃĤ
    -0.58
    POSITIVE LOGITS
    teenth
    1.92
    teen
    1.88
     months
    1.23
     hundred
    1.10
     weeks
    1.09
    een
    1.04
    eenth
    1.00
    fold
    0.97
     Months
    0.96
     thousand
    0.94
    Activations Density 0.031%

    No Known Activations