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. 9-RES-JB
    6. 11053
    Prev
    Next
    INDEX
    Explanations

    phrases related to procedures or activities

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence endings in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minion
    -0.75
     implied
    -0.74
     stationary
    -0.70
     maiden
    -0.70
     calf
    -0.69
     docks
    -0.69
     mate
    -0.67
    aeus
    -0.67
     docking
    -0.67
    ŃĶ
    -0.65
    POSITIVE LOGITS
     Fortunately
    1.33
     Few
    1.22
     Regardless
    1.21
     Nonetheless
    1.21
     Thankfully
    1.21
     Luckily
    1.19
     Understanding
    1.18
     Below
    1.18
     Nevertheless
    1.17
     Among
    1.16
    Activations Density 0.493%

    No Known Activations