© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1325
    Prev
    Next
    INDEX
    Explanations

    terms related to cryptocurrencies, blockchain, and investments

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and abbreviations related to technical or scientific terminology

    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
    irlf
    -0.72
    ¶ħ
    -0.69
     Osw
    -0.69
    retched
    -0.67
    assian
    -0.67
    izu
    -0.67
     Frie
    -0.66
    akable
    -0.66
    bern
    -0.65
    azard
    -0.65
    POSITIVE LOGITS
     tends
    1.31
     differs
    1.25
     comprises
    1.18
     behaves
    1.15
     involves
    1.15
     encompasses
    1.14
     lacks
    1.14
     consists
    1.14
     refers
    1.14
     is
    1.14
    Activations Density 0.433%

    No Known Activations