© 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. 4-RES-JB
    11. 22022
    Prev
    Next
    INDEX
    Explanations

    scientific abstracts or research-related terms

    oai_token-act-pair · gpt-3.5-turbo

    academic section headings, particularly "Abstract" and "Introduction."

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

    No Comments

    Negative Logits
    milo
    -0.69
     wont
    -0.67
     rou
    -0.66
     reps
    -0.65
     grandchildren
    -0.64
     stewards
    -0.64
     seats
    -0.64
     scrimmage
    -0.63
     torque
    -0.62
     ramp
    -0.62
    POSITIVE LOGITS
    Abstract
    1.17
    GROUND
    0.91
     Introduction
    0.87
     References
    0.86
     Abstract
    0.86
     Languages
    0.83
     Definitions
    0.82
    Introduction
    0.80
     Purpose
    0.79
    monary
    0.79
    Activations Density 0.022%

    No Known Activations