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. 3-RES-JB
    6. 11588
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "what happened."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arta
    -0.92
    mens
    -0.83
    hart
    -0.81
    ware
    -0.80
    reci
    -0.80
    hetically
    -0.79
    ently
    -0.76
    urdy
    -0.74
    stood
    -0.73
    urry
    -0.72
    POSITIVE LOGITS
    EStream
    0.84
    cffffcc
    0.80
     happening
    0.75
     Canaver
    0.75
     Ambro
    0.73
     happen
    0.72
     wrong
    0.71
     occurring
    0.71
     Hoff
    0.70
     unfolding
    0.70
    Activations Density 0.035%

    No Known Activations