© 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. 0-RES-JB
    11. 1348
    Prev
    Next
    INDEX
    Explanations

    names of a specific person, "Claire."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly names mentioned multiple times

    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
    minecraft
    -0.93
    soType
    -0.86
     INF
    -0.82
    Mob
    -0.77
     Flavoring
    -0.74
    ItemTracker
    -0.73
    NBA
    -0.72
     Shooter
    -0.71
     Immunity
    -0.71
     Railroad
    -0.70
    POSITIVE LOGITS
     Claire
    2.28
     Hod
    2.06
     Hed
    1.41
     Clare
    1.27
     Bates
    1.21
     cater
    1.16
     Hendricks
    1.15
     Laurel
    1.15
     Durant
    1.13
     Cliff
    1.11
    Activations Density 0.047%

    No Known Activations