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. 3027
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "minivan"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "minutes."

    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
    Forge
    -0.67
    ÙIJ
    -0.64
    Ranked
    -0.63
    kefeller
    -0.63
     Crusade
    -0.63
     Piercing
    -0.63
     Legion
    -0.62
    ATHER
    -0.60
    Enhanced
    -0.59
    geist
    -0.58
    POSITIVE LOGITS
    nesota
    1.14
    utes
    1.09
    iatures
    1.06
    neapolis
    1.02
    otaur
    1.02
    usc
    0.92
    isters
    0.88
    imens
    0.87
    istered
    0.87
    entary
    0.86
    Activations Density 0.006%

    No Known Activations