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. 0-RES-JB
    6. 21085
    Prev
    Next
    INDEX
    Explanations

    phrases related to Edward Snowden

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Edward Snowden

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     combined
    -0.68
    Num
    -0.67
     Mid
    -0.65
     pots
    -0.63
     carb
    -0.62
     autos
    -0.62
     prem
    -0.61
     combo
    -0.61
     kn
    -0.61
     Races
    -0.61
    POSITIVE LOGITS
     Snowden
    3.85
    Snow
    2.03
     Greenwald
    1.92
     Assange
    1.88
    NSA
    1.77
     NSA
    1.75
     WikiLeaks
    1.50
     whistleblower
    1.47
     Wikileaks
    1.47
     Clapper
    1.41
    Activations Density 0.017%

    No Known Activations