© 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. 20221
    Prev
    Next
    INDEX
    Explanations

    mentions about natural disasters, environmental issues, and technology

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" in various contexts

    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
    ãĥ³ãĤ¸
    -0.74
     Everywhere
    -0.73
     Parenthood
    -0.71
    ãĤº
    -0.71
    amily
    -0.71
    nces
    -0.70
    ãĥīãĥ©ãĤ´ãĥ³
    -0.69
    ĪĴ
    -0.69
    çļ
    -0.68
    Offline
    -0.67
    POSITIVE LOGITS
     thereby
    0.97
     ushered
    0.90
     therefore
    0.87
     thus
    0.87
     consequently
    0.87
     vowed
    0.86
     secondly
    0.85
     avoids
    0.85
     urged
    0.84
     expects
    0.83
    Activations Density 0.256%

    No Known Activations