© 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. 4-RES-JB
    11. 7351
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "it's time to" is used

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "time to" indicating urgency or a call to action

    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
    soDeliveryDate
    -1.00
     Advertisement
    -0.76
    hent
    -0.76
    VPN
    -0.75
    Sold
    -0.72
    TION
    -0.71
    raped
    -0.67
    listed
    -0.67
    Wan
    -0.64
    need
    -0.64
    POSITIVE LOGITS
     settle
    1.13
     celebrate
    1.07
     conserve
    1.01
     revisit
    1.00
     compensate
    0.99
     finish
    0.99
     prepare
    0.97
     accumulate
    0.96
     fulfil
    0.96
     relax
    0.96
    Activations Density 0.090%

    No Known Activations