© 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. 11-RES-JB
    11. 7837
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "The"

    oai_token-act-pair · gpt-3.5-turbo

    the word "The"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thereby
    -0.74
    Ò
    -0.72
    ––
    -0.71
     theirs
    -0.70
     regardless
    -0.69
     anyway
    -0.68
     without
    -0.67
     elsewhere
    -0.67
    .*
    -0.67
     according
    -0.66
    POSITIVE LOGITS
    resa
    1.46
    odore
    1.45
    orem
    1.22
    ories
    1.17
    atre
    1.13
    oret
    1.11
     Basics
    1.07
    sis
    0.93
     Difference
    0.91
     Story
    0.90
    Activations Density 0.342%

    No Known Activations