© 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. 10117
    Prev
    Next
    INDEX
    Explanations

    comparisons between different entities

    oai_token-act-pair · gpt-3.5-turbo

    references to comparisons and connections between entities or concepts

    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
    ĺħ
    -0.62
    enthal
    -0.50
    Discuss
    -0.50
    watching
    -0.49
    ©
    -0.49
     experimentation
    -0.47
    struction
    -0.47
     Mechdragon
    -0.47
     Giant
    -0.47
     Oaks
    -0.47
    POSITIVE LOGITS
     dots
    1.34
     to
    0.91
    MpServer
    0.88
     toget
    0.87
     closely
    0.80
     thereto
    0.76
     favorably
    0.75
     together
    0.73
     directly
    0.72
     securely
    0.71
    Activations Density 0.203%

    No Known Activations