© 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. 12062
    Prev
    Next
    INDEX
    Explanations

    descriptions or discussions related to specific situations or locations

    oai_token-act-pair · gpt-3.5-turbo
    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
    ODUCT
    -0.80
    TIT
    -0.69
    Cod
    -0.66
     Marketplace
    -0.66
    Specific
    -0.66
    Eth
    -0.65
    Notable
    -0.62
    ``
    -0.61
    Overview
    -0.61
    Snow
    -0.60
    POSITIVE LOGITS
    xual
    0.96
     plates
    0.89
    naires
    0.85
    ioned
    0.81
    tons
    0.79
    eering
    0.78
    aires
    0.76
     boards
    0.74
     toilets
    0.73
     plate
    0.72
    Activations Density 0.731%

    No Known Activations