© 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. 1-RES-JB
    11. 23207
    Prev
    Next
    INDEX
    Explanations

    phrases related to time, progression, and activities happening over a period

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a recurring time frame or period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illary
    -0.83
     partName
    -0.71
    女
    -0.70
    arium
    -0.69
    udes
    -0.66
    ¯¯¯¯
    -0.65
    UE
    -0.64
    BILITY
    -0.62
     correction
    -0.62
    Downloadha
    -0.62
    POSITIVE LOGITS
    haul
    1.03
    lord
    0.96
    tones
    0.95
    lander
    0.92
    whel
    0.91
    lap
    0.90
    drive
    0.89
    ensibly
    0.88
    hang
    0.87
    lay
    0.85
    Activations Density 0.009%

    No Known Activations