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. 21276
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and actions

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that indicate formal speech or statements made by individuals

    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
     Hydra
    -0.70
     acceler
    -0.70
     mosaic
    -0.68
     hydra
    -0.65
    ĪĴ
    -0.65
     bumps
    -0.62
     Minotaur
    -0.62
     tower
    -0.61
     gel
    -0.61
     waterfall
    -0.61
    POSITIVE LOGITS
    Speaking
    1.61
    Writing
    1.37
    Calling
    1.29
    Asked
    1.26
     Speaking
    1.24
    Refer
    1.15
    Interested
    1.13
    Talking
    1.11
    Amid
    1.06
    Discuss
    1.05
    Activations Density 0.313%

    No Known Activations