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

    Neuronpedia

    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. 7533
    Prev
    Next
    INDEX
    Explanations

    dates, locations, and events related to historical incidents

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and times in historical events

    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
     persuasion
    -0.90
     boycot
    -0.86
     polygamy
    -0.82
     invite
    -0.80
     appoint
    -0.80
    isan
    -0.78
     fav
    -0.78
     affili
    -0.77
     empowerment
    -0.77
     invites
    -0.76
    POSITIVE LOGITS
    Engineers
    1.42
    NASA
    1.08
    Scientists
    1.05
     Nasa
    1.04
    Crash
    0.97
    Emergency
    0.96
    Witness
    0.96
    Crew
    0.95
    Investigators
    0.94
     Orbital
    0.94
    Activations Density 0.618%

    No Known Activations