© 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. 11-RES-JB
    11. 2630
    Prev
    Next
    INDEX
    Explanations

    phrases related to heat absorption and release

    oai_token-act-pair · gpt-3.5-turbo

    terms related to energy transfer and environmental impact

    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
     Mock
    -0.67
     Wag
    -0.67
    practice
    -0.65
    ploma
    -0.65
     Dare
    -0.64
     WARN
    -0.63
     Tale
    -0.62
    ĪĴ
    -0.62
    review
    -0.62
    reements
    -0.61
    POSITIVE LOGITS
     nutrients
    1.19
     gases
    1.06
     combustion
    1.03
     molecules
    1.03
     into
    1.03
     ions
    1.03
     electrons
    1.01
     efficiently
    0.98
     dioxide
    0.97
     absorbed
    0.97
    Activations Density 0.272%

    No Known Activations