© 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. 4-RES-JB
    6. 4107
    Prev
    Next
    INDEX
    Explanations

    phrases related to making commitments

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "commit" and its variations, indicating a focus on dedication or obligation

    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
     Ain
    -0.70
    adish
    -0.70
     complexion
    -0.68
    addin
    -0.65
    phe
    -0.63
     allergies
    -0.61
    dayName
    -0.61
     Flavoring
    -0.61
    nz
    -0.61
     Takeru
    -0.61
    POSITIVE LOGITS
     committed
    0.88
    itent
    0.82
    acts
    0.81
    venant
    0.81
    erences
    0.79
    ependence
    0.77
     committing
    0.77
     suicide
    0.74
    commit
    0.73
     commits
    0.73
    Activations Density 0.017%

    No Known Activations