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. 10005
    Prev
    Next
    INDEX
    Explanations

    words related to shutting down or closure

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "shut down."

    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
     endors
    -0.70
     enthus
    -0.63
    orthy
    -0.61
    inen
    -0.61
     deserve
    -0.60
    Allah
    -0.60
     purified
    -0.60
    chev
    -0.60
    uld
    -0.59
    yne
    -0.59
    POSITIVE LOGITS
    river
    0.84
    downs
    0.75
    DOWN
    0.75
    iflower
    0.73
    down
    0.69
    rolled
    0.68
    wind
    0.66
    ipolar
    0.65
    votes
    0.65
     Interstate
    0.63
    Activations Density 0.031%

    No Known Activations