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. 3486
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific institutions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to various institutions or entities

    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
    arella
    -0.75
    fman
    -0.72
    hips
    -0.70
    lets
    -0.66
    lins
    -0.65
    balls
    -0.65
    leck
    -0.64
    zai
    -0.64
    vind
    -0.64
    wagen
    -0.63
    POSITIVE LOGITS
     Philippines
    0.96
     Ancients
    0.93
     Netherlands
    0.90
     United
    0.88
     Arts
    0.86
     Hundred
    0.82
     Holy
    0.81
     Judiciary
    0.80
     Tenth
    0.77
     same
    0.77
    Activations Density 0.088%

    No Known Activations