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. 5139
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental responsibility and sustainability

    oai_token-act-pair · gpt-3.5-turbo

    scientific explanations and definitions related to biology and human behavior

    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
    SPONSORED
    -0.93
    Syrian
    -0.80
    Iraq
    -0.74
    çīĪ
    -0.74
    YP
    -0.73
    irin
    -0.73
    wered
    -0.72
    Ohio
    -0.72
    Syria
    -0.70
    IDA
    -0.70
    POSITIVE LOGITS
     inherently
    1.11
     complex
    0.96
     finite
    0.90
     imperfect
    0.88
     complicated
    0.87
     differently
    0.87
     thri
    0.82
     intrinsically
    0.81
     notoriously
    0.81
     subjective
    0.80
    Activations Density 0.740%

    No Known Activations