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. 7-RES-JB
    6. 22286
    Prev
    Next
    INDEX
    Explanations

    references to political and philosophical ideas that contrast or prioritize certain concepts such as democracy, ideology, security, and profit

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal governance and ethics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soon
    -0.61
    oso
    -0.59
     Catch
    -0.58
     WATCHED
    -0.57
    almost
    -0.57
    hot
    -0.56
    mma
    -0.56
    repre
    -0.55
     ASA
    -0.55
     +++
    -0.53
    POSITIVE LOGITS
     nor
    0.99
     anymore
    0.96
     altogether
    0.89
     ones
    0.81
     guiActiveUn
    0.79
     versa
    0.72
     necessarily
    0.71
     itself
    0.69
     outright
    0.69
     anything
    0.67
    Activations Density 0.494%

    No Known Activations