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. 3-RES-JB
    6. 8576
    Prev
    Next
    INDEX
    Explanations

    specific mentions of a place named "Pekka"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name or identifier

    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
    ACTED
    -0.69
     vested
    -0.66
     contrace
    -0.66
     FANT
    -0.66
     redistributed
    -0.65
     suppressing
    -0.63
     AMERICA
    -0.63
    ãģĤ
    -0.62
     exha
    -0.62
     cort
    -0.62
    POSITIVE LOGITS
    nown
    1.31
    enstein
    1.04
    anism
    1.03
    eker
    1.00
    kies
    0.99
    kers
    0.98
    ek
    0.98
    edIn
    0.97
    owitz
    0.96
    ules
    0.95
    Activations Density 0.013%

    No Known Activations