Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 16947
    Prev
    Next
    INDEX
    Explanations

    answers starting with "Yes"

    oai_token-act-pair · gpt-3.5-turbo

    affirmative responses or confirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.77
    RAW
    -0.73
     externalToEVAOnly
    -0.72
    lines
    -0.71
    versions
    -0.71
     fart
    -0.71
    tein
    -0.70
    actionDate
    -0.70
    rosse
    -0.69
    inventoryQuantity
    -0.69
    POSITIVE LOGITS
    terday
    1.22
     Yes
    1.10
     yes
    1.02
     YES
    0.92
     sir
    0.88
    Yes
    0.80
     Nope
    0.78
     Yeah
    0.75
     Yep
    0.75
    umph
    0.74
    Activations Density 0.013%

    No Known Activations