© 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. 0-RES-JB
    11. 19770
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named "Tate"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names associated with specific individuals

    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
     Hawai
    -0.81
    NetMessage
    -0.73
    Haw
    -0.73
     Finnish
    -0.69
     mer
    -0.68
     Blizz
    -0.67
     Finland
    -0.67
     surn
    -0.66
     hail
    -0.65
     drift
    -0.65
    POSITIVE LOGITS
     Tate
    3.69
     Ramsey
    1.60
     Sanchez
    1.24
     Assange
    1.14
     Parsons
    1.12
     Barnett
    1.11
     Rubin
    1.06
    aston
    1.05
     Bentley
    1.05
     Atkins
    1.04
    Activations Density 0.028%

    No Known Activations