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. 12-RES-JB
    6. 15137
    Prev
    Next
    INDEX
    Explanations

    references to political and economic topics, specifically in the context of legislative measures and proposals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to specific legislative proposals or bills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    keeper
    -0.73
     marrow
    -0.58
     Barron
    -0.57
     Lazarus
    -0.56
    folk
    -0.56
     Mem
    -0.55
    llo
    -0.55
     recite
    -0.55
     Term
    -0.54
     Kendrick
    -0.54
    POSITIVE LOGITS
    aganda
    1.64
    ulsion
    1.46
    osed
    1.34
    ulsive
    1.21
    onents
    1.19
    onent
    1.15
    ylene
    1.14
    ensity
    1.13
    agate
    1.09
    hetic
    1.09
    Activations Density 0.020%

    No Known Activations