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. 3-RES-JB
    6. 11585
    Prev
    Next
    INDEX
    Explanations

    words related to racial diversity and demographics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of racial or ethnic descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.85
     Vinyl
    -0.72
    ļé
    -0.71
    erker
    -0.70
     Dragonbound
    -0.63
    İĭ
    -0.63
     Peaks
    -0.63
    Cod
    -0.62
    YC
    -0.62
     Clan
    -0.62
    POSITIVE LOGITS
    rha
    1.03
    vana
    0.98
    cles
    0.90
    andom
    0.89
    ror
    0.88
    mingham
    0.88
    ROR
    0.85
    ilateral
    0.85
    nie
    0.84
    rr
    0.84
    Activations Density 0.015%

    No Known Activations