© 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. 11-RES-JB
    11. 21344
    Prev
    Next
    INDEX
    Explanations

    events or time periods related to wars or revolutions

    oai_token-act-pair · gpt-3.5-turbo

    references to historical events and their aftermath

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ahead
    -0.78
    iton
    -0.78
    SPONSORED
    -0.74
    vier
    -0.74
    ERY
    -0.74
    pher
    -0.74
    notation
    -0.74
    eers
    -0.72
    emouth
    -0.72
     besides
    -0.71
    POSITIVE LOGITS
     Soviet
    1.20
     USSR
    1.18
     1960
    1.17
     Bolshevik
    1.16
     1970
    1.15
     Cold
    1.15
     1930
    1.14
     1980
    1.14
     uphe
    1.11
     Soviets
    1.11
    Activations Density 0.249%

    No Known Activations