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. 8-RES-JB
    6. 12082
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "As" and potentially containing a person's name

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "As" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accordingly
    -0.82
     thereto
    -0.72
     respons
    -0.70
     snipp
    -0.69
    indal
    -0.68
    "}],"
    -0.66
     recip
    -0.66
     moreover
    -0.66
    obbies
    -0.64
    ologically
    -0.64
    POSITIVE LOGITS
    reetings
    0.71
    ynchronous
    0.70
    chwitz
    0.68
     wildfires
    0.66
     NASCAR
    0.65
     Injury
    0.63
     Tropical
    0.62
    worldly
    0.62
     Donald
    0.62
    zbollah
    0.61
    Activations Density 0.191%

    No Known Activations