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

    Neuronpedia

    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. 7-RES-JB
    11. 7270
    Prev
    Next
    INDEX
    Explanations

    words related to programming languages, specifically Postgres and Django

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lad
    -0.74
    abin
    -0.71
    lements
    -0.69
    indal
    -0.67
     Lamp
    -0.67
    yrinth
    -0.67
    problem
    -0.67
    bard
    -0.66
     contingency
    -0.66
     Anim
    -0.66
    POSITIVE LOGITS
    £
    0.98
    $
    0.97
    ±
    0.95
    ãĥł
    0.95
    $$$$
    0.91
    \/\/
    0.90
     ±
    0.89
    @@@@
    0.89
     ¥
    0.88
    ©
    0.87
    Activations Density 0.152%

    No Known Activations