© 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. 8-RES-JB
    11. 3422
    Prev
    Next
    INDEX
    Explanations

    results related to actions and events with a narrative style

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values or measurements related to significant actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pand
    -0.63
     Xi
    -0.62
     charm
    -0.60
     poisoned
    -0.59
     ideal
    -0.57
    eco
    -0.57
     vot
    -0.56
    tones
    -0.56
     popul
    -0.56
     Cyborg
    -0.56
    POSITIVE LOGITS
    Eventually
    1.13
    SPONSORED
    1.13
    ³³³³
    1.08
    Then
    0.97
    Later
    0.96
    Suddenly
    0.96
    Upon
    0.94
    Advertisement
    0.92
    PHOTOS
    0.91
    Soon
    0.90
    Activations Density 0.438%

    No Known Activations