© 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. 17651
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or rules

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the existence of quantities or types of items

    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
    Initialized
    -0.72
    BuyableInstoreAndOnline
    -0.71
    Americans
    -0.64
     Niet
    -0.61
    roit
    -0.61
    doms
    -0.61
    Dear
    -0.60
    inventoryQuantity
    -0.57
     incompet
    -0.57
    Malley
    -0.57
    POSITIVE LOGITS
     currently
    1.07
     also
    1.04
     no
    0.96
     NO
    0.94
     plenty
    0.92
     tons
    0.90
    currently
    0.89
     lots
    0.87
     ALSO
    0.83
     several
    0.83
    Activations Density 0.116%

    No Known Activations