© 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. 8-RES-JB
    11. 2552
    Prev
    Next
    INDEX
    Explanations

    values related to increasing percentages or numbers

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating numerical comparisons involving changes or differences over time

    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
    Shift
    -0.71
    successfully
    -0.71
    agy
    -0.71
    é¾įåĸļ士
    -0.68
    igent
    -0.68
    leneck
    -0.66
    blance
    -0.65
    erto
    -0.65
    ira
    -0.65
    resy
    -0.64
    POSITIVE LOGITS
     afar
    0.98
     whence
    0.93
     baseline
    0.85
     scratch
    0.71
     conception
    0.68
     1929
    0.62
     inception
    0.60
     yesterday
    0.60
     previous
    0.60
     Tycoon
    0.59
    Activations Density 0.066%

    No Known Activations