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. 10547
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific religious or cultural belief system

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of "arian," implying contexts involving specific ideologies or identities

    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
    entry
    -0.68
    err
    -0.67
    redd
    -0.66
    pty
    -0.66
    same
    -0.66
    berman
    -0.65
    ura
    -0.65
    pless
    -0.64
    bench
    -0.64
    arton
    -0.63
    POSITIVE LOGITS
    arian
    1.09
    ism
    0.92
    cies
    0.92
    ity
    0.84
    arians
    0.80
    amental
    0.79
    omics
    0.77
    naire
    0.77
    ial
    0.77
    itarian
    0.76
    Activations Density 0.015%

    No Known Activations