Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21098
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "rew."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Drew" or related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tant
    -0.70
     Ig
    -0.70
     sin
    -0.63
     ivory
    -0.61
    士
    -0.61
     lymph
    -0.60
     paired
    -0.60
     sales
    -0.59
     Vu
    -0.59
     ultr
    -0.59
    POSITIVE LOGITS
    rew
    4.68
    rown
    1.38
    raft
    1.34
    romeda
    1.29
    rows
    1.28
    row
    1.27
    rafted
    1.17
     Rew
    1.16
    ream
    1.14
    resh
    1.12
    Activations Density 0.011%

    No Known Activations