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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 7530
    Prev
    Next
    INDEX
    Explanations

    phrases related to protests and activism

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to protests and expressions of social justice

    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
     supplement
    -0.80
     chronological
    -0.77
     resear
    -0.74
     pacing
    -0.73
     shrew
    -0.72
     refining
    -0.71
     refin
    -0.70
     illust
    -0.67
     manuscript
    -0.67
     novel
    -0.67
    POSITIVE LOGITS
    Allah
    1.03
    ahu
    1.01
    hello
    0.94
    RIP
    0.94
    Jesus
    0.94
    ratulations
    0.92
    bye
    0.92
    God
    0.90
    TRUMP
    0.89
    Fuck
    0.88
    Activations Density 0.377%

    No Known Activations