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. 5575
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooperation and collaboration

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that indicate relationships or connections between ideas

    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
    bidden
    -0.76
    kson
    -0.70
    thal
    -0.68
    got
    -0.68
    thought
    -0.67
    arthed
    -0.63
    ged
    -0.63
    ces
    -0.63
    forced
    -0.62
    edIn
    -0.62
    POSITIVE LOGITS
     cultivate
    1.30
     satisfy
    1.29
     engage
    1.25
     stimulate
    1.24
     promote
    1.23
     create
    1.23
     regulate
    1.22
     manipulate
    1.22
     distribute
    1.21
     defend
    1.21
    Activations Density 0.790%

    No Known Activations