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. 8-RES-JB
    6. 21608
    Prev
    Next
    INDEX
    Explanations

    mentions of prayer and religious belief, particularly related to Islam

    oai_token-act-pair · gpt-3.5-turbo

    references to religious practices or traditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ymm
    -0.72
    irection
    -0.69
    GW
    -0.65
     Pog
    -0.65
    oret
    -0.65
    PDF
    -0.63
    Publisher
    -0.61
     Gamble
    -0.61
    Emer
    -0.61
    aba
    -0.59
    POSITIVE LOGITS
     respectively
    1.10
     goddamn
    0.85
     fuckin
    0.83
     fucking
    0.81
    ))))
    0.80
    NetMessage
    0.79
     blah
    0.79
     shit
    0.78
    !".
    0.77
    etc
    0.76
    Activations Density 1.655%

    No Known Activations