© 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. 17241
    Prev
    Next
    INDEX
    Explanations

    commands or instructions related to software installation and coding

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to software installation and app development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     outwe
    -0.78
     Lilly
    -0.77
     cherished
    -0.72
     valued
    -0.72
     disappro
    -0.71
     polic
    -0.69
     unexplained
    -0.69
     upheld
    -0.68
     sustained
    -0.68
     prized
    -0.67
    POSITIVE LOGITS
    Setup
    1.37
    Install
    1.22
    STEP
    1.19
     Setup
    1.19
    Step
    1.13
    setup
    1.11
    Installation
    1.10
    Requirements
    1.09
    ETHOD
    1.09
    METHOD
    1.03
    Activations Density 0.264%

    No Known Activations