© 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. 2369
    Prev
    Next
    INDEX
    Explanations

    phrases that express interconnectedness and balance

    oai_token-act-pair · gpt-3.5-turbo

    references to elements of storytelling and narrative interconnectedness

    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
     Shutdown
    -0.85
     Pension
    -0.66
     retired
    -0.64
     Caucus
    -0.64
    ourt
    -0.63
     bailed
    -0.62
     Bust
    -0.61
     amnesty
    -0.61
     Bunker
    -0.61
     Bloomberg
    -0.61
    POSITIVE LOGITS
     intertw
    1.11
     resemb
    1.00
     subconscious
    0.99
     individuality
    0.98
     meanings
    0.98
     unconsciously
    0.97
     interacts
    0.95
     communicates
    0.95
     intangible
    0.93
     manifests
    0.92
    Activations Density 0.505%

    No Known Activations