© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8535
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving or providing opportunities, advantages, or ideas to someone or something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate providing opportunities or advantages

    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
     Deaths
    -0.76
    arb
    -0.65
    oice
    -0.62
     Taxes
    -0.62
     Accord
    -0.61
     dies
    -0.60
    LLOW
    -0.60
    verend
    -0.59
    cens
    -0.59
    essel
    -0.57
    POSITIVE LOGITS
     impetus
    1.35
     opportunity
    1.28
     advantage
    1.23
     chance
    1.23
     foothold
    1.20
     incentive
    1.17
     insight
    1.16
     leverage
    1.14
     excuse
    1.13
     flexibility
    1.11
    Activations Density 0.208%

    No Known Activations