© 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. 10-RES-JB
    11. 16666
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent events, investigations, and outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muse
    -0.75
     salesman
    -0.72
     newsletters
    -0.72
     Lonely
    -0.72
     Pledge
    -0.71
    holders
    -0.70
    docs
    -0.68
    holder
    -0.67
     adop
    -0.64
     warranties
    -0.64
    POSITIVE LOGITS
     caused
    1.16
     perpetrated
    1.16
     occurring
    1.11
     preceded
    1.08
     attributed
    1.06
     happening
    1.02
     triggered
    1.01
     inflicted
    1.00
     fatal
    1.00
     traced
    0.94
    Activations Density 0.162%

    No Known Activations