© 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. 8-RES-JB
    11. 2655
    Prev
    Next
    INDEX
    Explanations

    dates and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    temporal references related to events and dates

    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
    ¬¼
    -0.91
     lately
    -0.76
    reated
    -0.71
    Ħ¢
    -0.70
    infeld
    -0.69
     ingenious
    -0.69
    ħĭ
    -0.69
     tended
    -0.68
    uras
    -0.67
    assed
    -0.67
    POSITIVE LOGITS
     2019
    1.15
     2021
    0.96
     Deadline
    0.89
     2020
    0.89
    soDeliveryDate
    0.89
     tomorrow
    0.87
     2018
    0.85
     deadline
    0.85
     TBD
    0.84
    Tickets
    0.84
    Activations Density 0.514%

    No Known Activations