© 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. 8-RES-JB
    11. 8275
    Prev
    Next
    INDEX
    Explanations

    terms related to wars, specifically World War II

    oai_token-act-pair · gpt-3.5-turbo

    references to World War II

    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
    OGR
    -0.80
    obook
    -0.71
    ITY
    -0.69
    Asset
    -0.68
    */(
    -0.66
     KE
    -0.62
     snipp
    -0.61
     answ
    -0.60
     scaff
    -0.59
    iquid
    -0.58
    POSITIVE LOGITS
     II
    0.98
    lords
    0.95
    lord
    0.95
     III
    0.90
    bler
    0.83
    planes
    0.83
    ombat
    0.82
    riors
    0.79
    rior
    0.76
    orthy
    0.75
    Activations Density 0.019%

    No Known Activations