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. 11689
    Prev
    Next
    INDEX
    Explanations

    phrases related to awards or official recognitions

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of "orders," particularly in a formal or governmental context

    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
    vae
    -0.78
    ãĤ¨ãĥ«
    -0.71
    pmwiki
    -0.70
    ctory
    -0.70
    td
    -0.69
    rower
    -0.67
    dden
    -0.67
    minist
    -0.67
    ãĥ©
    -0.67
    lished
    -0.66
    POSITIVE LOGITS
     Order
    1.26
    eous
    1.04
    lies
    0.96
    eering
    0.92
    liness
    0.92
    Order
    0.86
     Sequence
    0.83
     Orders
    0.80
    eers
    0.76
     order
    0.72
    Activations Density 0.009%

    No Known Activations