© 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. 7774
    Prev
    Next
    INDEX
    Explanations

    words related to changes in quantity or degree, such as rates, demand, reduction, and disparities

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data and metrics related to rates and changes 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
    cott
    -0.72
    letes
    -0.65
    GGGGGGGG
    -0.63
    interstitial
    -0.62
    ilingual
    -0.62
    apego
    -0.62
    boss
    -0.61
    CLUD
    -0.61
    ensitive
    -0.59
    recated
    -0.59
    POSITIVE LOGITS
     direction
    0.89
     expectancy
    0.86
     fortunes
    0.83
     magnitude
    0.80
     capacity
    0.76
     proportions
    0.76
     intensity
    0.73
    ahime
    0.73
     standings
    0.72
    '>
    0.72
    Activations Density 0.350%

    No Known Activations