© 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 EvalsExportsinterp-engineNEWAPI 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. 11666
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "lightning" alongside an adjective or descriptor

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Lightning Network."

    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
    glers
    -0.91
    nee
    -0.74
    VICE
    -0.74
    eday
    -0.73
    cha
    -0.72
    ablishment
    -0.72
    dit
    -0.71
    lied
    -0.71
    nil
    -0.71
    eto
    -0.70
    POSITIVE LOGITS
    bolt
    1.25
     bolt
    1.16
     bolts
    1.09
     rod
    1.05
     Bolt
    0.98
    storms
    0.93
    fast
    0.92
     rods
    0.89
     strike
    0.85
     strikes
    0.84
    Activations Density 0.046%

    No Known Activations