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. 3-RES-JB
    6. 7461
    Prev
    Next
    INDEX
    Explanations

    references to the version control platform GitHub

    oai_token-act-pair · gpt-3.5-turbo

    mentions of GitHub

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phal
    -0.76
    phe
    -0.69
    undai
    -0.69
    ecause
    -0.68
    igslist
    -0.68
    rug
    -0.67
    cum
    -0.65
    vati
    -0.64
    eal
    -0.63
    ̶
    -0.62
    POSITIVE LOGITS
     repository
    1.06
     repositories
    0.99
     Pages
    0.92
     GitHub
    0.86
     repo
    0.85
     Commons
    0.75
    usercontent
    0.73
     Username
    0.71
     Contribut
    0.70
     username
    0.69
    Activations Density 0.012%

    No Known Activations