Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 21074
    Prev
    Next
    INDEX
    Explanations

    phrases related to utopian or dystopian visions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to utopia and dystopia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    backer
    -0.65
    hips
    -0.65
     Drawn
    -0.64
     Radar
    -0.64
    graded
    -0.64
    Bridge
    -0.63
     Gladiator
    -0.62
     Cobra
    -0.62
    rons
    -0.62
     Analyst
    -0.60
    POSITIVE LOGITS
     ut
    4.35
    utf
    1.37
    Ut
    1.36
     Ut
    1.32
     utopian
    1.32
     dystop
    1.32
     UTF
    1.21
     UT
    1.09
    UTF
    1.03
     san
    0.94
    Activations Density 0.012%

    No Known Activations