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. 10-RES-JB
    6. 1541
    Prev
    Next
    INDEX
    Explanations

    organizations and entities, specifically those related to human rights, government, and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations or governmental bodies

    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
     runaway
    -0.70
    interstitial
    -0.69
    flush
    -0.69
    window
    -0.68
    rift
    -0.67
    adj
    -0.66
    thin
    -0.65
    animate
    -0.65
    death
    -0.65
     dstg
    -0.65
    POSITIVE LOGITS
     strives
    1.55
     intends
    1.54
     welcomes
    1.53
     respects
    1.49
     recognizes
    1.49
     believes
    1.42
     understands
    1.40
     hereby
    1.38
     expects
    1.36
     wishes
    1.34
    Activations Density 0.279%

    No Known Activations