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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 14253
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a summary or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "inclusion."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hower
    -0.68
    gaard
    -0.67
     Citation
    -0.66
     offending
    -0.64
    sworth
    -0.61
    fell
    -0.58
    Ö¼
    -0.58
    oru
    -0.58
    bidden
    -0.57
    deen
    -0.57
    POSITIVE LOGITS
    clusive
    1.03
     vain
    0.76
     moderation
    0.75
    clus
    0.73
    offensive
    0.72
     sudden
    0.72
    CLUS
    0.71
    effic
    0.69
     favor
    0.65
     goodness
    0.64
    Activations Density 0.049%

    No Known Activations