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. 7450
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a requirement or necessity to do something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating obligation or necessity

    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
     Emerging
    -0.72
    Recommended
    -0.69
     Guilty
    -0.68
     Rust
    -0.67
     Lambert
    -0.66
     Nort
    -0.65
     Emir
    -0.64
     Blueprint
    -0.62
     Globe
    -0.61
    Friend
    -0.61
    POSITIVE LOGITS
     rely
    1.18
     endure
    1.16
     contend
    1.10
     wait
    1.07
     fend
    1.05
     cope
    1.02
     intervene
    1.01
     overcome
    0.98
     confront
    0.97
     rethink
    0.95
    Activations Density 0.116%

    No Known Activations