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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 20493
    Prev
    Next
    INDEX
    Explanations

    sentences related to legal proceedings and communication

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal proceedings and public information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trak
    -0.72
     Rhythm
    -0.70
     Maintenance
    -0.67
     Accessories
    -0.65
     ANG
    -0.64
     Converted
    -0.64
     Warehouse
    -0.62
     Sunrise
    -0.62
    quartered
    -0.62
     accessory
    -0.61
    POSITIVE LOGITS
     aloud
    0.80
     jurors
    0.78
     unbiased
    0.77
     audiences
    0.76
     mainstream
    0.75
    relevant
    0.74
     impartial
    0.73
     policymakers
    0.72
     context
    0.71
     future
    0.71
    Activations Density 0.919%

    No Known Activations