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. 11869
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and civil rights issues, particularly focusing on religious freedom

    oai_token-act-pair · gpt-3.5-turbo

    references to religious freedom and its implications

    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
     Lans
    -0.77
    shown
    -0.71
    worthiness
    -0.70
     RELEASE
    -0.67
     Ago
    -0.66
     Completed
    -0.66
     Oper
    -0.64
    ptive
    -0.64
    llular
    -0.63
     Penet
    -0.63
    POSITIVE LOGITS
     extremists
    1.00
     fundamentalist
    0.91
     zeal
    0.91
     extremist
    0.90
     sensibilities
    0.89
     radicals
    0.88
     bible
    0.86
     ferv
    0.83
     extremism
    0.82
     protestors
    0.81
    Activations Density 0.316%

    No Known Activations