© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 9477
    Prev
    Next
    INDEX
    Explanations

    words related to delaying or postponing actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to postponement or delays in plans or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worn
    -0.72
    bleacher
    -0.72
    incial
    -0.71
    obbies
    -0.71
    usky
    -0.70
    ãĤ±
    -0.70
    liv
    -0.69
    arov
    -0.69
    iques
    -0.69
    arc
    -0.68
    POSITIVE LOGITS
     gratification
    1.29
     indefinitely
    1.26
     puberty
    1.05
     postp
    1.02
     until
    0.96
     deportation
    0.91
     till
    0.91
     delaying
    0.88
    uberty
    0.82
     deport
    0.82
    Activations Density 0.108%

    No Known Activations