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. 12101
    Prev
    Next
    INDEX
    Explanations

    terms related to technology companies or products

    oai_token-act-pair · gpt-3.5-turbo

    specific names of technology companies, operating systems, and related concepts

    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
    •Suppression Features Layer 8 GPT2 Small

    No Comments

    Negative Logits
     Lives
    -1.04
     Benefit
    -1.00
     Disorder
    -0.97
     Month
    -0.96
     Lover
    -0.96
     Accountability
    -0.95
     Lines
    -0.94
     Matter
    -0.94
     Thing
    -0.94
     Clause
    -0.93
    POSITIVE LOGITS
     democr
    0.82
    arians
    0.80
    fortunately
    0.79
     commons
    0.78
     tv
    0.78
    ensis
    0.77
     franc
    0.76
     americ
    0.75
     academy
    0.74
     communists
    0.72
    Activations Density 0.616%

    No Known Activations