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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 20246
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by nouns that indicate an opportunity or advantage

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate opportunities or advantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Accord
    -0.71
    anish
    -0.64
    ohm
    -0.64
    cue
    -0.59
     Deaths
    -0.59
     Transactions
    -0.59
    essel
    -0.58
     Cipher
    -0.57
    FontSize
    -0.56
    aten
    -0.56
    POSITIVE LOGITS
     opportunity
    1.36
     chance
    1.34
     impetus
    1.04
     insight
    1.03
     glimpse
    1.01
     opportunities
    0.98
     flexibility
    0.97
     headache
    0.94
     incentive
    0.94
     choice
    0.93
    Activations Density 0.183%

    No Known Activations