© 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. 0-RES-JB
    11. 9888
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names or locations that contain the word "Tan."

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with the name "Tan" and related variations

    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
    conom
    -0.80
     whe
    -0.72
     hippocamp
    -0.69
     fracking
    -0.68
     paralysis
    -0.66
     Lafayette
    -0.65
     rehe
    -0.65
    umps
    -0.63
    olph
    -0.62
     fractions
    -0.62
    POSITIVE LOGITS
     Tan
    3.79
    Tan
    3.20
     Tanaka
    1.68
     tan
    1.60
     Tanzania
    1.49
    tan
    1.45
     Tanner
    1.40
     Ng
    1.33
     Za
    1.22
     Shan
    1.17
    Activations Density 0.018%

    No Known Activations