© 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. 10-RES-JB
    11. 13672
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations or people, specifically with connections to the word "Pine"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adr
    -0.68
    ded
    -0.63
    ifts
    -0.62
    ä¹ĭ
    -0.61
    ifted
    -0.61
    IGHTS
    -0.60
    IFE
    -0.58
    Beck
    -0.57
    owship
    -0.57
     sorts
    -0.57
    POSITIVE LOGITS
    ilon
    0.99
    ongyang
    0.91
    asus
    0.89
    sylvania
    0.79
    olicy
    0.79
    aukee
    0.78
    odcast
    0.77
    lyak
    0.77
    emonium
    0.76
    eters
    0.76
    Activations Density 0.224%

    No Known Activations