© 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. 10-RES-JB
    11. 18735
    Prev
    Next
    INDEX
    Explanations

    mentions of military vessels and specific locations

    oai_token-act-pair · gpt-3.5-turbo

    references to naval ships and related geographic locations

    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
    ictions
    -1.09
    iction
    -0.89
    cms
    -0.79
     denomin
    -0.75
     sentence
    -0.74
     clutch
    -0.74
    */(
    -0.73
    anguage
    -0.73
    ifles
    -0.72
     coating
    -0.71
    POSITIVE LOGITS
     Liberty
    1.05
     Augusta
    1.04
     Canaveral
    1.04
     El
    1.00
     Kat
    0.98
     Britann
    0.98
     Martha
    0.97
     Reno
    0.97
     Olympia
    0.96
     Fort
    0.96
    Activations Density 0.147%

    No Known Activations