© 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. 10630
    Prev
    Next
    INDEX
    Explanations

    phrases indicating events or actions happening in a timely manner

    oai_token-act-pair · gpt-3.5-turbo

    temporal phrases and references to specific events or occasions

    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
    gans
    -0.72
     searched
    -0.66
     behaved
    -0.66
    wrong
    -0.65
    found
    -0.65
     penetrated
    -0.64
    haven
    -0.64
    leeve
    -0.63
    hor
    -0.62
    iste
    -0.60
    POSITIVE LOGITS
     Thanksgiving
    1.19
     Christmas
    1.16
     holidays
    1.14
     inauguration
    1.06
     unveiling
    1.00
     holiday
    0.99
     Halloween
    0.97
     Ramadan
    0.95
     finals
    0.94
     Easter
    0.93
    Activations Density 0.184%

    No Known Activations