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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 6663
    Prev
    Next
    INDEX
    Explanations

    names related to the name "Marg" followed by other characters, possibly part of people's names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Marg" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ninja
    -0.79
    atron
    -0.79
    ochet
    -0.73
     clan
    -0.68
     intel
    -0.67
     Naruto
    -0.67
     itch
    -0.66
    ãĤ»
    -0.66
     tubes
    -0.66
    utor
    -0.64
    POSITIVE LOGITS
     Marg
    4.05
    Marg
    2.83
    marg
    2.35
     marg
    1.99
     margin
    1.42
     margins
    1.36
    margin
    1.34
     Margaret
    1.09
     Laf
    1.06
     Gaw
    0.99
    Activations Density 0.015%

    No Known Activations