© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10175
    Prev
    Next
    INDEX
    Explanations

    references to historical events and figures, particularly in the context of Christianity and other historical periods

    oai_token-act-pair · gpt-3.5-turbo

    references to historical contexts and significant societal structures

    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
    govtrack
    -0.96
    bnb
    -0.91
    tackle
    -0.88
    Downloadha
    -0.77
    NetMessage
    -0.75
    heed
    -0.74
    mate
    -0.74
    ocket
    -0.74
    POSE
    -0.73
    ulnerability
    -0.73
    POSITIVE LOGITS
     nineteenth
    1.28
     Americas
    1.23
     twentieth
    1.22
     Balkans
    1.21
     eighteenth
    1.16
     1930
    1.12
     Ottoman
    1.09
     postwar
    1.09
     writings
    1.08
     USSR
    1.08
    Activations Density 0.210%

    No Known Activations