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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1206
    Prev
    Next
    INDEX
    Explanations

    proper names, specifically the name "John"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "John"

    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
     resil
    -0.82
    âĶĢ
    -0.80
    âĸĪ
    -0.71
    aza
    -0.71
     aval
    -0.69
     yuan
    -0.68
    URE
    -0.68
    upt
    -0.68
     appraisal
    -0.65
     âĹı
    -0.65
    POSITIVE LOGITS
     John
    3.13
    John
    2.76
     JOHN
    2.23
    john
    2.03
    JOHN
    1.96
     john
    1.89
     Johns
    1.68
     George
    1.61
     William
    1.60
     James
    1.57
    Activations Density 0.027%

    No Known Activations