© 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. 3-RES-JB
    11. 15527
    Prev
    Next
    INDEX
    Explanations

    references to the term "marshal" in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to marshals, both in the context of people and the term itself

    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
    lihood
    -0.78
    aughs
    -0.77
    OPLE
    -0.65
    products
    -0.63
     deaf
    -0.62
     impulse
    -0.62
    GROUP
    -0.61
     superficial
    -0.60
     tense
    -0.60
    NetMessage
    -0.60
    POSITIVE LOGITS
    mallow
    1.43
     marsh
    1.26
    alled
    1.10
    alling
    1.05
     Marshal
    1.05
    aling
    1.00
    ãĤ©
    1.00
    aled
    0.96
    alis
    0.93
    als
    0.91
    Activations Density 0.005%

    No Known Activations