© 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. 4-RES-JB
    11. 6254
    Prev
    Next
    INDEX
    Explanations

    the word "the" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    the term "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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     according
    -0.77
    âĢł
    -0.75
     Albania
    -0.74
     thereby
    -0.73
    Malley
    -0.64
    bourg
    -0.64
    /
    -0.64
    Britain
    -0.63
    ashington
    -0.62
     Romania
    -0.61
    POSITIVE LOGITS
     slightest
    1.21
     simplest
    1.13
     smallest
    1.12
     hardest
    1.12
     whole
    1.10
    ses
    1.07
     coolest
    1.04
     easiest
    1.04
     same
    1.04
     brightest
    1.03
    Activations Density 1.306%

    No Known Activations