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

    Neuronpedia

    APICircuit 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. 14371
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Lon Strickler"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and places

    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
    bush
    -0.76
     Pax
    -0.72
    gate
    -0.70
    dain
    -0.64
     Gupta
    -0.64
    ctic
    -0.63
     chrome
    -0.63
    itect
    -0.63
     browser
    -0.62
     sweating
    -0.61
    POSITIVE LOGITS
     Lob
    1.88
     Luna
    1.66
     Lar
    1.59
     Lon
    1.59
    L
    1.49
     Lak
    1.46
     Larson
    1.46
     LR
    1.46
     LF
    1.44
     Liu
    1.43
    Activations Density 0.078%

    No Known Activations