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. 5486
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental responsibility and sustainability

    oai_token-act-pair · gpt-3.5-turbo

    instances of negation often paired with the word "not."

    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
     Samar
    -0.66
     Monroe
    -0.66
     Drawn
    -0.61
     Mobil
    -0.60
     Irwin
    -0.59
     Folk
    -0.59
     Opportun
    -0.59
     advisers
    -0.59
     secretaries
    -0.59
     Paran
    -0.59
    POSITIVE LOGITS
    ï¸ı
    1.14
    ude
    0.87
    exist
    0.87
    udes
    0.87
    ember
    0.84
    ulty
    0.84
    iversary
    0.81
    iced
    0.80
    uge
    0.76
    ttle
    0.76
    Activations Density 0.436%

    No Known Activations