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. 11-RES-JB
    6. 3063
    Prev
    Next
    INDEX
    Explanations

    discussions related to market imperfections and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    statements highlighting societal flaws and criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dub
    -0.65
    ãĥĺ
    -0.64
     )]
    -0.62
     Springer
    -0.60
    çīĪ
    -0.58
     Originally
    -0.57
    Scroll
    -0.57
     Bund
    -0.56
    inder
    -0.55
     Chung
    -0.55
    POSITIVE LOGITS
     imperfect
    1.11
     plenty
    0.97
     undeniably
    0.96
     certainly
    0.95
     occasionally
    0.95
     unavoid
    0.90
     exist
    0.88
     nevertheless
    0.84
     undoubtedly
    0.84
     nuanced
    0.83
    Activations Density 0.706%

    No Known Activations