Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19092
    Prev
    Next
    INDEX
    Explanations

    mentions of the region Punjab

    oai_token-act-pair · gpt-3.5-turbo

    references to the Punjab region and related political topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bell
    -0.97
    awaru
    -0.83
    biz
    -0.82
    henko
    -0.78
    ety
    -0.77
    elong
    -0.76
    ages
    -0.76
    ischer
    -0.74
    bling
    -0.73
    resy
    -0.73
    POSITIVE LOGITS
     ILCS
    0.90
     Noise
    0.69
     Roads
    0.69
    ively
    0.68
    ãĤ¼ãĤ¦ãĤ¹
    0.67
    GGGGGGGG
    0.65
    ãĥĥãĥĪ
    0.65
    Agg
    0.64
     Violent
    0.63
     Roh
    0.63
    Activations Density 0.028%

    No Known Activations