© 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. 6-RES-JB
    11. 557
    Prev
    Next
    INDEX
    Explanations

    acronyms or abbreviations in the text

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to specific technical or scientific terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rimp
    -0.69
    izu
    -0.67
    taboola
    -0.66
    wcs
    -0.66
    aved
    -0.64
    -0.62
    rez
    -0.62
    bat
    -0.61
     âĢº
    -0.61
     Riley
    -0.60
    POSITIVE LOGITS
    DERR
    0.83
     inhibitors
    0.75
    OPA
    0.73
     holders
    0.72
    ATES
    0.72
    ERAL
    0.71
    senal
    0.69
     inhibitor
    0.67
    INESS
    0.67
    vantage
    0.65
    Activations Density 0.120%

    No Known Activations