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. 18167
    Prev
    Next
    INDEX
    Explanations

    mentions of corruption

    oai_token-act-pair · gpt-3.5-turbo

    references to corruption and its implications

    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
    leigh
    -0.81
    imus
    -0.74
    lee
    -0.72
    nee
    -0.71
     Advent
    -0.70
    AY
    -0.69
    thur
    -0.65
    liner
    -0.63
    tz
    -0.62
    aiden
    -0.62
    POSITIVE LOGITS
     scandals
    1.05
     corruption
    0.94
     graft
    0.89
    ulent
    0.87
     perpetrated
    0.87
     scandal
    0.81
     endemic
    0.81
     schemes
    0.80
     allegations
    0.80
     corrupt
    0.80
    Activations Density 0.056%

    No Known Activations