© 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 EvalsExportsinterp-engineNEWAPI 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. 19044
    Prev
    Next
    INDEX
    Explanations

    locations and quantities

    oai_token-act-pair · gpt-3.5-turbo

    specific mentions of individuals and quantities related to legal, social, or medical contexts

    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
     Rw
    -0.86
     Hung
    -0.85
     Tai
    -0.84
     WTO
    -0.84
    Tai
    -0.82
     Hut
    -0.81
     Rwanda
    -0.81
     Tus
    -0.80
    952
    -0.80
     Taiwan
    -0.79
    POSITIVE LOGITS
     Perry
    1.72
    Per
    1.41
     Perkins
    1.40
     PER
    1.22
     Per
    1.20
    PER
    1.19
     Perl
    1.15
    per
    1.05
     Percy
    0.93
     Perse
    0.93
    Activations Density 0.371%

    No Known Activations