© 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. 11534
    Prev
    Next
    INDEX
    Explanations

    phrases including a specific symbol "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    sections of text indicating numerical information or quantities

    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
    aeda
    -0.78
    ython
    -0.74
    awei
    -0.71
     ageing
    -0.70
     whilst
    -0.69
     nationality
    -0.68
    egal
    -0.67
    etheless
    -0.66
     scept
    -0.65
     Euros
    -0.65
    POSITIVE LOGITS
    CLOSE
    0.94
    Lt
    0.84
    âĸº
    0.81
    hello
    0.81
    Investigators
    0.80
     ..........
    0.76
    Norm
    0.76
    Bus
    0.76
     Related
    0.76
    Buy
    0.76
    Activations Density 0.404%

    No Known Activations