© 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. 2862
    Prev
    Next
    INDEX
    Explanations

    specific names, particularly the name "Annie," with a focus on various contexts such as people, locations, and events

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named "Annie" or "Nie."

    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
    iance
    -0.93
    yrinth
    -0.86
    ahime
    -0.75
    adem
    -0.74
    yrus
    -0.73
    threat
    -0.72
    esian
    -0.72
    inion
    -0.72
    wordpress
    -0.71
    utenberg
    -0.70
    POSITIVE LOGITS
     Mae
    1.01
    IELD
    0.90
    ENTS
    0.81
     Manson
    0.78
    llo
    0.77
     Hawkins
    0.77
    ãĤ¡
    0.76
     Ago
    0.74
     Caldwell
    0.73
     Oak
    0.72
    Activations Density 0.036%

    No Known Activations