© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 9535
    Prev
    Next
    INDEX
    Explanations

    names that include the prefix "Ol" followed by a single character

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Ol"

    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
    ãĥ¼ãĥĨãĤ£
    -1.03
    shapeshifter
    -0.77
     اÙĦ
    -0.75
     Whitman
    -0.75
     CLSID
    -0.74
    ãĤº
    -0.74
    DCS
    -0.72
    éļ
    -0.71
    è¦ļéĨĴ
    -0.71
    âķIJâķIJ
    -0.70
    POSITIVE LOGITS
    imar
    0.96
    okia
    0.93
    itates
    0.90
    oko
    0.90
    alia
    0.89
    ipop
    0.89
     Ol
    0.87
    adin
    0.86
    kil
    0.86
    athe
    0.85
    Activations Density 0.003%

    No Known Activations