© 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. 10-RES-JB
    11. 6308
    Prev
    Next
    INDEX
    Explanations

    charts, graphs, and estimates in text data

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe data visualizations or charts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.73
    rit
    -0.69
    matter
    -0.67
    fur
    -0.65
    Lago
    -0.65
    ubi
    -0.65
    Audio
    -0.62
    é¾įå
    -0.62
    utsu
    -0.62
    inating
    -0.61
    POSITIVE LOGITS
     how
    1.36
     percentages
    1.19
     averages
    1.14
     cumulative
    1.13
     percentage
    1.10
     median
    1.09
     approximate
    1.09
     average
    1.08
     trends
    1.06
     probabilities
    1.05
    Activations Density 0.199%

    No Known Activations