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. 11-RES-JB
    6. 16829
    Prev
    Next
    INDEX
    Explanations

    organizations and groups names related to government, community, and consumer-related issues

    oai_token-act-pair · gpt-3.5-turbo

    references to "Citizens" and related organizations or community groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liness
    -1.00
    nings
    -0.92
    liest
    -0.79
    gery
    -0.74
    Äĩ
    -0.72
    ema
    -0.71
    shr
    -0.71
    ð
    -0.70
    bing
    -0.69
    cé
    -0.69
    POSITIVE LOGITS
     Against
    0.97
     Affairs
    0.96
     Federation
    0.94
     Supported
    0.94
     Expend
    0.93
     Legal
    0.92
     Advice
    0.92
     Defender
    0.91
     Financial
    0.91
     Improvement
    0.91
    Activations Density 0.078%

    No Known Activations