© 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. 7443
    Prev
    Next
    INDEX
    Explanations

    words related to historical battles and events

    oai_token-act-pair · gpt-3.5-turbo

    references to historical battles

    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
    ascript
    -0.88
    ority
    -0.78
    ringe
    -0.77
     redistributed
    -0.76
     listing
    -0.72
    rency
    -0.69
     delegation
    -0.69
    ccording
    -0.67
     addressing
    -0.67
    address
    -0.67
    POSITIVE LOGITS
     Bunker
    1.11
     Hastings
    1.01
     Waterloo
    0.91
     Helm
    0.91
     Armageddon
    0.88
     Getty
    0.83
     Tours
    0.81
     Mount
    0.81
     Hearth
    0.79
     Pass
    0.79
    Activations Density 0.095%

    No Known Activations