© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 4273
    Prev
    Next
    INDEX
    Explanations

    words related to wartime and the postwar period

    oai_token-act-pair · gpt-3.5-turbo

    terms related to wartime and postwar contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uana
    -0.98
    essee
    -0.96
    Magikarp
    -0.91
    leon
    -0.88
    BOOK
    -0.81
    Choice
    -0.80
     Flavoring
    -0.80
    aceae
    -0.77
    Tile
    -0.76
    orse
    -0.75
    POSITIVE LOGITS
     wartime
    1.21
     pacif
    0.82
     Osw
    0.74
     Aerospace
    0.73
     dictator
    0.73
     1914
    0.72
     barracks
    0.70
     military
    0.70
     servic
    0.70
     Pact
    0.70
    Activations Density 0.012%

    No Known Activations