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. 0-RES-JB
    6. 20828
    Prev
    Next
    INDEX
    Explanations

    words related to the country of Eswatini

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific ethnic groups or cultural identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vest
    -0.69
    BIT
    -0.65
     BAT
    -0.61
     wound
    -0.61
     per
    -0.58
     bob
    -0.57
     gig
    -0.57
     TB
    -0.57
     Bigfoot
    -0.57
     cord
    -0.56
    POSITIVE LOGITS
    ese
    4.93
    ESE
    2.46
    esi
    1.40
    este
    1.16
    uese
    1.14
    esity
    1.03
    namese
    0.99
    esc
    0.97
    esh
    0.97
    iste
    0.97
    Activations Density 0.017%

    No Known Activations