© 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. 10-RES-JB
    11. 21826
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the phrase "X" or "Dragon Quest X"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming or game titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Feder
    -0.86
     Fisher
    -0.83
     Finn
    -0.80
     Donna
    -0.80
     oblig
    -0.77
     fisher
    -0.77
     Truman
    -0.74
     Lori
    -0.73
     servant
    -0.72
     Abraham
    -0.71
    POSITIVE LOGITS
    X
    1.95
     X
    1.61
    x
    1.55
    ax
    1.48
    ox
    1.46
    XL
    1.45
     Xen
    1.43
    XX
    1.40
    OX
    1.40
    AX
    1.37
    Activations Density 0.271%

    No Known Activations