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. 5-RES-JB
    6. 24540
    Prev
    Next
    INDEX
    Explanations

    references to legislative activities, especially related to specific areas or actions within a legislative body like a floor vote

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative bodies and their activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marketed
    -0.72
     kits
    -0.71
     behavi
    -0.70
     overdoses
    -0.68
     plent
    -0.67
     traff
    -0.64
    MAT
    -0.64
    CRIPTION
    -0.63
    AMI
    -0.62
    paralle
    -0.62
    POSITIVE LOGITS
    sembly
    1.13
    liament
    0.97
     Speaker
    0.97
     Elections
    0.96
     parliament
    0.95
     deliberations
    0.92
     elections
    0.91
     adjourn
    0.89
     tribunal
    0.89
     session
    0.87
    Activations Density 0.114%

    No Known Activations