© 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. 1-RES-JB
    11. 10236
    Prev
    Next
    INDEX
    Explanations

    mentions of funding or research grants

    oai_token-act-pair · gpt-3.5-turbo

    mentions of funding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Son
    -0.78
    opol
    -0.76
     Sunny
    -0.74
    Benz
    -0.73
    \/\/
    -0.70
     Ple
    -0.68
     Sed
    -0.68
    gro
    -0.66
     Yak
    -0.65
    washer
    -0.64
    POSITIVE LOGITS
     funding
    1.19
     Funding
    1.03
     financed
    1.02
     funded
    1.00
    funded
    1.00
     funds
    0.96
     financing
    0.95
    funding
    0.93
     allocations
    0.88
    interstitial
    0.87
    Activations Density 0.018%

    No Known Activations