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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 7096
    Prev
    Next
    INDEX
    Explanations

    tech-related words and phrases, possibly related to coding or software development

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     automobile
    -0.75
     suburban
    -0.73
     methamphetamine
    -0.73
     Greenwich
    -0.72
    SPONSORED
    -0.71
    kefeller
    -0.70
     economically
    -0.70
     Amtrak
    -0.69
     wealthier
    -0.68
     economics
    -0.68
    POSITIVE LOGITS
     spoiler
    1.09
     spoilers
    1.07
    ^^
    1.03
    ãĥİ
    1.02
     teaser
    0.95
     XD
    0.94
     haha
    0.94
    âĸł
    0.93
     Blizz
    0.91
     ãĥ
    0.91
    Activations Density 0.700%

    No Known Activations