Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22980
    Prev
    Next
    INDEX
    Explanations

    terms related to policy and advocacy efforts, particularly around social and political issues like climate change, gun control, and immigration reform

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases related to policy discussions and advocacy across various social issues

    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
     Athletic
    -0.79
    jac
    -0.79
    Īè
    -0.79
    AUT
    -0.72
    é¾įå
    -0.70
     Chess
    -0.68
    oyal
    -0.67
    uci
    -0.67
    yss
    -0.64
    )=(
    -0.64
    POSITIVE LOGITS
     worldwide
    0.76
     nationwide
    0.72
     campaigner
    0.69
     Amnesty
    0.68
     hotline
    0.66
     globally
    0.66
     uncertainties
    0.66
    iferation
    0.66
    backs
    0.65
     AMA
    0.64
    Activations Density 0.550%

    No Known Activations