Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 18734
    Prev
    Next
    INDEX
    Explanations

    words related to delay or postponement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to deferring or postponing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemTracker
    -0.81
    OPER
    -0.76
    Reviewer
    -0.75
    MT
    -0.73
    ̶
    -0.73
    hester
    -0.71
    Bad
    -0.70
     Passion
    -0.69
    VID
    -0.68
     Tonight
    -0.68
    POSITIVE LOGITS
     defer
    1.10
     deferred
    0.87
    ral
    0.86
    ments
    0.84
    minist
    0.80
    ptive
    0.78
    itures
    0.78
     gratification
    0.77
     adjud
    0.73
    ency
    0.73
    Activations Density 0.007%

    No Known Activations