© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 15768
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific magazine - Cosmopolitan

    oai_token-act-pair · gpt-3.5-turbo

    references to the magazine Cosmopolitan

    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
     flush
    -0.84
     deflation
    -0.75
     yen
    -0.73
     heel
    -0.73
     nig
    -0.71
     downward
    -0.70
    rontal
    -0.70
     upward
    -0.69
     samurai
    -0.69
     steady
    -0.69
    POSITIVE LOGITS
     Cos
    2.50
     Fle
    1.39
     Dom
    1.36
     Aud
    1.36
     Maxim
    1.29
     Cond
    1.23
    Cos
    1.21
     Est
    1.21
     Bott
    1.20
     Brands
    1.18
    Activations Density 0.015%

    No Known Activations