© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 24003
    Prev
    Next
    INDEX
    Explanations

    phrases related to software checking, scanning, and automatic detection

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to technical analysis and system processes in computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Study
    -0.74
     Advent
    -0.73
    Study
    -0.71
    backer
    -0.71
    united
    -0.68
    fal
    -0.67
    INGTON
    -0.66
    assault
    -0.65
    ilings
    -0.64
     Consortium
    -0.63
    POSITIVE LOGITS
     automatically
    1.05
     incoming
    0.87
     detects
    0.86
     dynamically
    0.80
     instantaneous
    0.75
     detect
    0.75
     inputs
    0.73
     autonom
    0.73
     vibrations
    0.72
     infrared
    0.71
    Activations Density 0.424%

    No Known Activations