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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 24046
    Prev
    Next
    INDEX
    Explanations

    phrases indicating events or actions that are scheduled to happen at a specific time in the future

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "until"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acus
    -0.87
    jac
    -0.75
    abet
    -0.74
    ictive
    -0.73
    ãĤ©
    -0.71
    usional
    -0.69
    ysis
    -0.68
    Ģ
    -0.67
    ãĥīãĥ©
    -0.67
    roid
    -0.67
    POSITIVE LOGITS
     after
    1.13
     AFTER
    1.10
     2021
    1.10
     2022
    1.04
     2019
    1.03
     2024
    1.02
     January
    1.00
     2030
    0.99
     2020
    0.98
     December
    0.98
    Activations Density 0.060%

    No Known Activations