© 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. 9-RES-JB
    11. 14861
    Prev
    Next
    INDEX
    Explanations

    code-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    elements related to computer programming and coding concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Directory
    -0.65
    conservancy
    -0.65
     Baltic
    -0.63
    çīĪ
    -0.61
     Austral
    -0.60
     Bangalore
    -0.57
     âĶľâĶĢâĶĢ
    -0.57
    izons
    -0.57
     Scandinav
    -0.57
     Slate
    -0.56
    POSITIVE LOGITS
     punishments
    0.82
    Result
    0.79
     punishment
    0.79
     outcome
    0.74
     payoff
    0.74
     outcomes
    0.73
     deed
    0.72
     deeds
    0.71
     speeches
    0.71
     shots
    0.70
    Activations Density 1.282%

    No Known Activations