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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-RES-JB
    6. 17523
    Prev
    Next
    INDEX
    Explanations

    instances of the word "program"

    oai_token-act-pair · gpt-3.5-turbo

    references to programming concepts and specific programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ween
    -0.72
     Fiat
    -0.68
    xious
    -0.67
     Tall
    -0.63
     exting
    -0.62
     stake
    -0.61
     liquids
    -0.61
     toll
    -0.59
    ushima
    -0.59
     basin
    -0.58
    POSITIVE LOGITS
    mable
    1.57
    matically
    1.30
    mers
    1.14
    matic
    1.12
    atically
    0.93
    program
    0.93
    manship
    0.88
     programs
    0.84
     skelet
    0.82
     Gutenberg
    0.82
    Activations Density 0.028%

    No Known Activations