© 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. 22149
    Prev
    Next
    INDEX
    Explanations

    words related to Greek letter organizations or chapters

    oai_token-act-pair · gpt-3.5-turbo

    references to Greek life organizations and their chapters

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.91
    ãĤ¤ãĥĪ
    -0.88
    ãĥī
    -0.84
     Assass
    -0.80
    FTWARE
    -0.76
    ãģ¾
    -0.75
    ãĤ½
    -0.74
    éĹĺ
    -0.74
    士
    -0.73
    ãĥĸ
    -0.73
    POSITIVE LOGITS
    terness
    0.94
    enta
    0.83
    aim
    0.75
     Nu
    0.75
    isine
    0.75
    adian
    0.75
    lesi
    0.74
    awar
    0.74
    itudes
    0.73
    anus
    0.72
    Activations Density 0.019%

    No Known Activations