© 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. 9-RES-JB
    6. 2801
    Prev
    Next
    INDEX
    Explanations

    the word "be" and variations of it in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there will be," indicating future occurrences or predictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zer
    -0.68
    plug
    -0.64
    buster
    -0.60
    rix
    -0.59
    azar
    -0.59
    arta
    -0.59
    era
    -0.58
    oot
    -0.57
    tip
    -0.56
    strip
    -0.56
    POSITIVE LOGITS
     plenty
    1.14
     no
    0.96
     exceptions
    0.93
     ample
    0.93
     lots
    0.93
     repercussions
    0.91
     some
    0.90
    nces
    0.88
     fewer
    0.87
     enough
    0.85
    Activations Density 0.041%

    No Known Activations