© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 699
    Prev
    Next
    INDEX
    Explanations

    time-related references, specifically highlighting periods of two to four years

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference time durations, particularly "two" and "three" years or decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wrapper
    -0.76
    isky
    -0.73
    racuse
    -0.70
    aughter
    -0.69
    eteria
    -0.65
    vu
    -0.64
    vec
    -0.62
    still
    -0.62
    ãĤ¨ãĥ«
    -0.61
    anger
    -0.61
    POSITIVE LOGITS
     weeks
    1.42
     years
    1.40
     months
    1.38
     decades
    1.34
     seasons
    1.25
     days
    1.19
     administrations
    1.19
     summers
    1.14
     generations
    1.13
    years
    1.12
    Activations Density 0.039%

    No Known Activations