© 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. 4-RES-JB
    11. 17169
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the surname "Thompson."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Thompson."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utive
    -0.91
    76561
    -0.81
    eas
    -0.77
    spring
    -0.71
    stract
    -0.70
    bnb
    -0.70
    dyl
    -0.70
    cle
    -0.70
    statement
    -0.69
    dit
    -0.69
    POSITIVE LOGITS
     Browne
    0.83
    stown
    0.81
    sonian
    0.76
    acks
    0.72
     Thompson
    0.70
     Gunn
    0.69
     Brothers
    0.68
    itton
    0.68
     Bros
    0.67
    urai
    0.66
    Activations Density 0.009%

    No Known Activations