© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 3704
    Prev
    Next
    INDEX
    Explanations

    names related to the term "Sus"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people, particularly those with the name "Sus"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.74
     stakes
    -0.66
     wills
    -0.61
     Doomsday
    -0.60
     forging
    -0.60
     ledger
    -0.59
     lessons
    -0.58
     Ukrainians
    -0.57
     reorgan
    -0.57
     directors
    -0.57
    POSITIVE LOGITS
    pect
    1.50
    pected
    1.46
    pecting
    1.39
    pects
    1.38
    pic
    1.35
    annah
    1.35
    cept
    1.14
    pir
    1.07
    itized
    0.99
    sex
    0.98
    Activations Density 0.045%

    No Known Activations