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. 18150
    Prev
    Next
    INDEX
    Explanations

    chemical reactions and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to allergic reactions and their causes

    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
    Ă
    -0.98
    Ā
    -0.97
    ú
    -0.97
    Ĝ
    -0.97
    é¾įå¥
    -0.97
    ø
    -0.97
    ö
    -0.97
    À
    -0.97
    Ě
    -0.97
    ù
    -0.97
    POSITIVE LOGITS
     layer
    0.53
     hook
    0.51
     anymore
    0.50
     or
    0.50
     hooks
    0.50
     ±
    0.50
    ").
    0.49
     notation
    0.48
    )?
    0.48
     )
    0.48
    Activations Density 0.071%

    No Known Activations