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. 4-RES-JB
    6. 21497
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Islam" along with closely related discussions or sentiments

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Islam."

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

    No Comments

    Negative Logits
     Rober
    -0.81
     WD
    -0.71
     Seah
    -0.69
     EAR
    -0.65
     DEC
    -0.65
    asper
    -0.65
    TY
    -0.64
    EAR
    -0.62
     Rockefeller
    -0.62
    dain
    -0.61
    POSITIVE LOGITS
    ophobic
    1.58
    ophobia
    1.52
    ophob
    1.20
    abad
    1.10
    zai
    0.95
    ics
    0.93
    etics
    0.91
    icals
    0.89
    obia
    0.89
    ification
    0.88
    Activations Density 0.009%

    No Known Activations