© 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. 15977
    Prev
    Next
    INDEX
    Explanations

    titles or phrases related to historical wars

    oai_token-act-pair · gpt-3.5-turbo

    references to various wars and battles throughout history

    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
    pta
    -0.85
    vana
    -0.83
    ffer
    -0.82
    nce
    -0.79
    nea
    -0.75
    oen
    -0.74
    nsic
    -0.71
    ascript
    -0.70
    vp
    -0.68
    inez
    -0.68
    POSITIVE LOGITS
     wills
    1.29
     attrition
    1.05
     sexes
    0.99
     Roses
    0.92
     sorts
    0.88
     ideologies
    0.85
     Ideas
    0.84
     ideas
    0.84
     clans
    0.83
     nerves
    0.82
    Activations Density 0.093%

    No Known Activations