© 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. 0-RES-JB
    6. 1661
    Prev
    Next
    INDEX
    Explanations

    the word "This" occurring at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "This."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fond
    -0.62
     passers
    -0.60
     ambul
    -0.58
     prevailing
    -0.57
    aires
    -0.55
     wound
    -0.54
     officers
    -0.54
     barg
    -0.53
    ank
    -0.53
     waist
    -0.52
    POSITIVE LOGITS
     This
    2.59
     These
    2.01
    This
    1.91
     THIS
    1.65
     Thus
    1.57
     There
    1.53
     Although
    1.53
     That
    1.52
     Since
    1.51
     Therefore
    1.51
    Activations Density 0.055%

    No Known Activations