© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15138
    Prev
    Next
    INDEX
    Explanations

    instances of the word "too" indicating excess or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize excessiveness or the term "too."

    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
    ãĥ©ãĥ³
    -0.70
    iliation
    -0.59
    tains
    -0.59
    ief
    -0.57
     Source
    -0.53
    execute
    -0.53
    ollo
    -0.53
    ARA
    -0.52
     princip
    -0.52
     Advocate
    -0.51
    POSITIVE LOGITS
     too
    3.34
    too
    2.50
     Too
    2.27
    Too
    1.84
     overly
    1.35
     excessively
    1.32
     insufficient
    1.21
     undue
    1.11
     unnecessarily
    1.09
     excessive
    1.08
    Activations Density 0.041%

    No Known Activations