Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17837
    Prev
    Next
    INDEX
    Explanations

    terms related to the name "McK"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly those with the last name "McK."

    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
     simul
    -0.71
    itar
    -0.67
     lie
    -0.67
    ouri
    -0.66
    uri
    -0.65
     Uri
    -0.65
    cler
    -0.65
    forcement
    -0.64
     besie
    -0.64
    sale
    -0.63
    POSITIVE LOGITS
     McK
    3.56
     Twe
    1.11
     McF
    1.08
    Mc
    1.03
     McM
    1.02
     McKenzie
    1.01
     Vaughn
    1.00
     McKenna
    1.00
     McGu
    0.96
     Hopkins
    0.94
    Activations Density 0.018%

    No Known Activations