© 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. 16050
    Prev
    Next
    INDEX
    Explanations

    technical terms or concepts related to computing and technology

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to technology and infrastructure

    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
    Finish
    -0.69
    Hig
    -0.65
     chromosome
    -0.62
     Canal
    -0.62
     allele
    -0.62
    Attempt
    -0.61
    Witness
    -0.59
    ãĥ©ãĥ³
    -0.58
    ãĥį
    -0.57
    Assistant
    -0.57
    POSITIVE LOGITS
    paces
    1.45
    hips
    1.31
    ynthesis
    1.25
    etting
    1.18
    mith
    1.16
    hip
    1.15
    ystem
    1.14
    pace
    1.09
    ets
    1.05
    chool
    1.03
    Activations Density 0.428%

    No Known Activations