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. 6-RES-JB
    6. 22682
    Prev
    Next
    INDEX
    Explanations

    statements or beliefs related to education and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express belief or acceptance of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Regulation
    -0.68
     Scale
    -0.64
    forcement
    -0.63
     precedent
    -0.61
     timetable
    -0.61
     protocol
    -0.60
     Issue
    -0.60
    plate
    -0.59
    Scale
    -0.59
     legality
    -0.57
    POSITIVE LOGITS
     themselves
    1.17
    selves
    1.10
     whom
    0.94
     selves
    0.86
     heirs
    0.83
    who
    0.83
     congreg
    0.82
     alike
    0.81
     backgrounds
    0.80
     deserving
    0.80
    Activations Density 1.111%

    No Known Activations