© 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. 2-RES-JB
    11. 17132
    Prev
    Next
    INDEX
    Explanations

    the name "ary" or words ending in "ary"

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the suffix "-ary."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odder
    -0.70
    GREEN
    -0.65
    ortium
    -0.63
     Survivor
    -0.63
    âĵĺ
    -0.62
    essee
    -0.61
    ļéĨĴ
    -0.60
     Variant
    -0.60
    semb
    -0.60
    estern
    -0.59
    POSITIVE LOGITS
    ature
    0.79
    oga
    0.73
    otes
    0.72
    ary
    0.71
    otic
    0.70
    ansas
    0.69
    cery
    0.69
    acy
    0.68
    ussia
    0.67
    akh
    0.67
    Activations Density 0.013%

    No Known Activations