© 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. 2-RES-JB
    11. 23730
    Prev
    Next
    INDEX
    Explanations

    terms related to business partnerships and growth

    oai_token-act-pair · gpt-3.5-turbo

    terms related to business growth and partnerships in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amput
    -0.60
     wounding
    -0.57
     pard
    -0.57
    SPONSORED
    -0.56
     graves
    -0.54
     poems
    -0.53
     Reconstruction
    -0.53
     Allaah
    -0.51
     prayer
    -0.51
     coerc
    -0.51
    POSITIVE LOGITS
     OEM
    0.72
     developers
    0.72
     proprietary
    0.70
     IoT
    0.69
     NVIDIA
    0.68
     SDK
    0.68
     customers
    0.68
     chipset
    0.67
     backend
    0.66
     portfolio
    0.66
    Activations Density 3.745%

    No Known Activations