© 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. 3-RES-JB
    11. 14791
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names containing the word "Ley"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Ley" and variations of the term "originally."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ible
    -0.68
    Oracle
    -0.67
    Fly
    -0.67
    Austin
    -0.66
    isks
    -0.66
    letcher
    -0.65
    aus
    -0.65
    chet
    -0.64
     Hut
    -0.63
    Draft
    -0.63
    POSITIVE LOGITS
    rogens
    0.75
     contrace
    0.72
     confir
    0.72
    inally
    0.71
    mination
    0.71
    aceous
    0.70
    inez
    0.69
    tesy
    0.69
    £ı
    0.69
    NetMessage
    0.68
    Activations Density 0.015%

    No Known Activations