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. 10-RES-JB
    6. 21947
    Prev
    Next
    INDEX
    Explanations

    keywords related to criticism and controversy

    oai_token-act-pair · gpt-3.5-turbo

    mentions of advocacy, criticism, and political reactions regarding social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shalt
    -0.67
     reproduction
    -0.63
     giveaway
    -0.58
     rect
    -0.57
     operates
    -0.57
     misdem
    -0.55
     grace
    -0.55
    ãĥĺ
    -0.54
     survived
    -0.54
     supplementary
    -0.54
    POSITIVE LOGITS
     alike
    1.21
     who
    1.03
    who
    0.90
    ervatives
    0.88
     worried
    0.88
     concerned
    0.82
     appalled
    0.82
     wary
    0.79
     alarmed
    0.78
     skeptical
    0.78
    Activations Density 0.322%

    No Known Activations