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. 15127
    Prev
    Next
    INDEX
    Explanations

    requests and offers involving actions and locations

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

    conditional phrases related to requests and offers

    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
    ñ
    -0.98
    ò
    -0.97
    £ı
    -0.95
    embedreportprint
    -0.92
    ý
    -0.92
    ÷
    -0.92
     externalTo
    -0.92
    Ė
    -0.92
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.92
    ę
    -0.92
    POSITIVE LOGITS
     marry
    1.23
     accompany
    1.21
     babys
    1.10
     kidnap
    0.99
     escort
    0.99
     borrow
    0.98
     meet
    0.97
     kill
    0.95
     arrange
    0.92
     bury
    0.91
    Activations Density 0.333%

    No Known Activations