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. 14726
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and advanced concepts

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns and terms related to politics, conflict, and societal issues

    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
    herer
    -0.63
    agame
    -0.59
    aminer
    -0.59
    mma
    -0.57
    bsite
    -0.56
    agonist
    -0.56
    akening
    -0.54
    etter
    -0.54
    jri
    -0.53
    uden
    -0.53
    POSITIVE LOGITS
     backgrounds
    0.69
     proportions
    0.65
     emergencies
    0.64
     groups
    0.63
     sources
    0.62
     associations
    0.61
     travellers
    0.61
     warfare
    0.61
     organs
    0.60
     interests
    0.60
    Activations Density 0.956%

    No Known Activations