© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 7341
    Prev
    Next
    INDEX
    Explanations

    references to source code hosting platform GitHub

    oai_token-act-pair · gpt-3.5-turbo

    references to GitHub and related platforms

    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
    phal
    -0.88
    rug
    -0.76
    phe
    -0.73
    eal
    -0.72
    ̶
    -0.70
    vati
    -0.70
    igslist
    -0.69
    EVA
    -0.69
    othing
    -0.68
    respond
    -0.67
    POSITIVE LOGITS
     GitHub
    0.92
     repository
    0.91
     repositories
    0.90
     Pages
    0.87
     Username
    0.76
     Github
    0.74
    halla
    0.73
     Git
    0.70
     Hacker
    0.70
     Commons
    0.69
    Activations Density 0.005%

    No Known Activations