© 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. 3425
    Prev
    Next
    INDEX
    Explanations

    mentions of things that are pint-sized or small versions of something else

    oai_token-act-pair · gpt-3.5-turbo

    references to miniature versions ofobjects or concepts

    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
    âķIJâķIJ
    -0.67
    rer
    -0.66
    Û
    -0.65
    rite
    -0.64
    yer
    -0.64
    Ö¼
    -0.63
    addock
    -0.62
     Grind
    -0.62
    lain
    -0.61
    iquette
    -0.61
    POSITIVE LOGITS
    ature
    1.06
    atur
    0.97
    ocular
    0.92
     mini
    0.88
    mini
    0.80
     sized
    0.76
    atures
    0.75
    oby
    0.72
    istered
    0.71
     Mini
    0.71
    Activations Density 0.005%

    No Known Activations