© 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. 2-RES-JB
    6. 18749
    Prev
    Next
    INDEX
    Explanations

    phrases related to time and dates, specifically focusing on the Indian Standard Time (IST) timezone

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the acronym "IST" and its variations related to time or schedules

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    house
    -0.72
    esville
    -0.71
    houses
    -0.70
    es
    -0.69
    clus
    -0.69
    ktop
    -0.67
    don
    -0.65
    tainment
    -0.64
    isers
    -0.62
     charm
    -0.61
    POSITIVE LOGITS
     IST
    0.99
    ARGET
    0.96
    AN
    0.92
    ANI
    0.89
    CHAT
    0.80
    IJ
    0.80
    ür
    0.80
    PIN
    0.80
    OY
    0.79
    IST
    0.78
    Activations Density 0.009%

    No Known Activations