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. 1-RES-JB
    6. 4325
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or laws

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legislative measures or laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lanka
    -0.75
    kus
    -0.69
    cro
    -0.67
    stocks
    -0.66
    playing
    -0.65
    hiba
    -0.64
    adies
    -0.63
    gets
    -0.63
    lasses
    -0.62
     Univers
    -0.61
    POSITIVE LOGITS
     ordinance
    1.25
     ordinances
    1.15
    inances
    1.14
    inarily
    0.86
    nance
    0.84
     enforcement
    0.75
    ufact
    0.75
    alities
    0.73
     droid
    0.73
    inance
    0.73
    Activations Density 0.006%

    No Known Activations