© 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. 13981
    Prev
    Next
    INDEX
    Explanations

    phrases related to performing tasks or activities

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts

    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
    SPONSORED
    -0.79
    GGGG
    -0.71
    hower
    -0.70
    ontent
    -0.68
    ONSORED
    -0.67
     "$:/
    -0.63
    VERTISEMENT
    -0.63
    neau
    -0.63
     Provides
    -0.62
    quished
    -0.61
    POSITIVE LOGITS
     unthinkable
    1.27
     same
    1.25
    same
    1.12
     math
    1.11
     opposite
    1.05
     maths
    1.00
     homework
    0.97
     job
    0.97
     trick
    0.97
     groundwork
    0.95
    Activations Density 0.055%

    No Known Activations