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. 9-RES-JB
    6. 9412
    Prev
    Next
    INDEX
    Explanations

    terms related to societal structures and power dynamics, particularly focusing on communities, establishments, and elites

    oai_token-act-pair · gpt-3.5-turbo

    references to various communities and their relationships with societal structures or power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.79
    ishable
    -0.71
    opl
    -0.70
     Plate
    -0.70
    ocol
    -0.66
    itial
    -0.64
    planet
    -0.62
    aring
    -0.62
     Kard
    -0.61
    ĨĴ
    -0.60
    POSITIVE LOGITS
     itself
    0.80
    members
    0.79
    ariat
    0.76
     hierarchy
    0.76
     members
    0.74
     alike
    0.72
     reacted
    0.71
     interven
    0.69
    leaders
    0.69
     assembled
    0.68
    Activations Density 0.201%

    No Known Activations