© 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. 2-RES-JB
    11. 8291
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the term "Knights"

    oai_token-act-pair · gpt-3.5-turbo
    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
    PROV
    -0.68
    aciously
    -0.66
    advert
    -0.64
    perature
    -0.61
    mble
    -0.61
    ãĤ¨ãĥ«
    -0.61
    gel
    -0.60
    essage
    -0.59
    à
    -0.59
    ience
    -0.59
    POSITIVE LOGITS
     Templar
    1.25
    mares
    1.08
     Templ
    1.05
     Knights
    1.03
    hip
    0.85
     Radiant
    0.84
    mare
    0.78
    aido
    0.78
    warm
    0.78
    doms
    0.77
    Activations Density 0.013%

    No Known Activations