© 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. 22438
    Prev
    Next
    INDEX
    Explanations

    specific times of scheduled events

    oai_token-act-pair · gpt-3.5-turbo

    specific times of day, particularly in the 'pm' context

    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
    wikipedia
    -0.65
    quished
    -0.63
     acknowled
    -0.62
     Flavoring
    -0.62
    leans
    -0.62
    char
    -0.62
    strings
    -0.61
     resemb
    -0.57
     behav
    -0.57
     careg
    -0.56
    POSITIVE LOGITS
    endment
    1.09
     EDT
    1.03
    essage
    0.99
     EST
    0.98
    sterdam
    0.93
    ueller
    0.93
    issions
    0.85
     PST
    0.83
    pm
    0.83
    obile
    0.82
    Activations Density 0.015%

    No Known Activations