© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3252
    Prev
    Next
    INDEX
    Explanations

    proper names and specific details in a text

    oai_token-act-pair · gpt-3.5-turbo

    information related to births and familial relationships

    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
     conventions
    -0.93
     administrations
    -0.82
     pressures
    -0.79
     promotions
    -0.78
     sponsors
    -0.75
     endorsements
    -0.75
     gimm
    -0.74
     manag
    -0.74
     principals
    -0.74
     defenses
    -0.72
    POSITIVE LOGITS
     Rohingya
    0.95
     Mohamed
    0.87
     Qiao
    0.86
     Devi
    0.84
     Chloe
    0.83
     Melania
    0.83
     Sophie
    0.83
     plaintiff
    0.83
     Zoe
    0.82
     Yaz
    0.82
    Activations Density 0.842%

    No Known Activations