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. 4320
    Prev
    Next
    INDEX
    Explanations

    terms related to racial identity, especially the word "biracial"

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with biracial identity

    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
    OSP
    -0.63
     UNIVERS
    -0.62
     Result
    -0.62
    oji
    -0.62
    PF
    -0.62
    ebus
    -0.61
    afort
    -0.59
    eq
    -0.59
    Finish
    -0.59
    defined
    -0.59
    POSITIVE LOGITS
    mingham
    1.17
     bir
    1.15
    thing
    0.95
     fir
    0.87
    Bir
    0.85
     bund
    0.75
     Birch
    0.74
    gin
    0.74
     horizont
    0.73
    estone
    0.72
    Activations Density 0.006%

    No Known Activations