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. 2-RES-JB
    6. 22727
    Prev
    Next
    INDEX
    Explanations

    names of individuals and places

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiment or criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dickinson
    -0.74
    etheless
    -0.73
     pause
    -0.70
     eternity
    -0.67
     shade
    -0.65
    wcs
    -0.64
     diam
    -0.63
     todd
    -0.63
     VIEW
    -0.63
     reflection
    -0.63
    POSITIVE LOGITS
    based
    1.14
    cert
    1.04
    san
    1.02
    sama
    1.00
    sized
    0.98
    kun
    0.97
    derived
    0.95
    nom
    0.95
    affiliated
    0.95
    themed
    0.94
    Activations Density 0.373%

    No Known Activations