© 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. 13845
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, often with details like age, occupation, or background

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their characteristics or statuses

    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
    cation
    -0.83
    Episode
    -0.82
    ageddon
    -0.81
    views
    -0.81
    soType
    -0.80
    wcsstore
    -0.78
    encies
    -0.77
    inventoryQuantity
    -0.77
    lations
    -0.75
     VIDEOS
    -0.75
    POSITIVE LOGITS
     young
    1.25
     teenager
    1.21
     woman
    1.18
     teenage
    1.15
     former
    1.13
     retired
    1.11
     Frenchman
    1.09
     wealthy
    1.07
     classmate
    1.06
     longtime
    1.06
    Activations Density 0.214%

    No Known Activations