© 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. 16672
    Prev
    Next
    INDEX
    Explanations

    the phrase "one by one."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the word "by."

    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
    CLOSE
    -0.66
    atsu
    -0.57
     cheat
    -0.53
    acterial
    -0.51
     plur
    -0.50
    ucha
    -0.49
    fat
    -0.49
    DVD
    -0.49
    ythm
    -0.48
     esports
    -0.48
    POSITIVE LOGITS
    oubtedly
    0.61
     BaseType
    0.57
     ItemLevel
    0.56
     [|
    0.54
     Emin
    0.53
    sylv
    0.53
    aldi
    0.53
     Alternatively
    0.52
     respectively
    0.52
     Located
    0.51
    Activations Density 1.549%

    No Known Activations