© 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. 3732
    Prev
    Next
    INDEX
    Explanations

    programming-related instructions and steps, particularly those involving actions and methods

    oai_token-act-pair · gpt-3.5-turbo

    instructions or steps related to performing actions and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    cellence
    -0.81
    ONSORED
    -0.79
    scar
    -0.78
    uca
    -0.78
    usk
    -0.76
    reath
    -0.72
    endon
    -0.71
    rica
    -0.71
    egal
    -0.70
    sole
    -0.69
    POSITIVE LOGITS
     commands
    1.47
     functions
    1.44
     dependencies
    1.37
     libraries
    1.32
     APIs
    1.29
     parameters
    1.29
     helper
    1.28
     constants
    1.28
     macros
    1.27
     optimizations
    1.27
    Activations Density 0.221%

    No Known Activations