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. 1-RES-JB
    6. 11012
    Prev
    Next
    INDEX
    Explanations

    phrases related to things being on the brink of significant change or action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating impending change or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tan
    -0.74
    add
    -0.73
    pocket
    -0.72
    atto
    -0.70
    war
    -0.67
     retrieved
    -0.65
     downloaded
    -0.65
     performed
    -0.65
    raft
    -0.64
    packs
    -0.64
    POSITIVE LOGITS
     verge
    1.18
    ï¸
    0.92
     unbeliev
    0.85
     brink
    0.85
    terness
    0.81
    ÃĽ
    0.74
    veyard
    0.69
     Ples
    0.68
     comprom
    0.67
    avascript
    0.65
    Activations Density 0.003%

    No Known Activations