© 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. 1-RES-JB
    11. 11182
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in "arily" or related to formal legal or military actions

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating a manner or degree

    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
    erers
    -0.74
     Stellar
    -0.72
     Springfield
    -0.68
    busters
    -0.67
     Fires
    -0.66
    erer
    -0.66
     Flag
    -0.66
     Flood
    -0.64
     Explos
    -0.64
     Farmers
    -0.64
    POSITIVE LOGITS
    arily
    1.35
    ignty
    0.87
     speaking
    0.82
    avage
    0.74
     ratified
    0.73
    pha
    0.73
     disadvantages
    0.73
    ++++++++++++++++
    0.72
    ãĤ´ãĥ³
    0.72
    mares
    0.71
    Activations Density 0.004%

    No Known Activations