© 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. 6-RES-JB
    11. 15276
    Prev
    Next
    INDEX
    Explanations

    mentions of possessing or acquiring something

    oai_token-act-pair · gpt-3.5-turbo

    references to obtaining or having something, specifically the word "one."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¬
    -0.71
    osponsors
    -0.69
    ories
    -0.68
    ãĤ±
    -0.67
    inity
    -0.66
     Vaugh
    -0.66
    ooks
    -0.66
    ãĥ©ãĥ³
    -0.62
    DEF
    -0.62
    etz
    -0.62
    POSITIVE LOGITS
     hundred
    1.01
     Hundred
    0.98
     thing
    0.92
     thousand
    0.85
     dimensional
    0.83
     million
    0.81
     ounce
    0.77
    handedly
    0.75
     Thousand
    0.74
     Piece
    0.74
    Activations Density 0.118%

    No Known Activations