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. 8-RES-JB
    6. 18814
    Prev
    Next
    INDEX
    Explanations

    terms related to revolution or revolutionary movements

    oai_token-act-pair · gpt-3.5-turbo

    references to revolutionary movements and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ews
    -0.85
    eenth
    -0.83
    Downloadha
    -0.83
    pel
    -0.82
    nery
    -0.81
    room
    -0.81
    bag
    -0.80
    andra
    -0.79
    ed
    -0.79
    ophon
    -0.78
    POSITIVE LOGITS
     minded
    0.96
    axy
    0.80
     zeal
    0.79
     qualities
    0.78
     tendencies
    0.77
    TY
    0.76
     thinking
    0.75
     impulses
    0.74
     aspects
    0.73
     significance
    0.73
    Activations Density 0.084%

    No Known Activations