© 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. 17878
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific person or location, particularly the word "Benedict" and the concept of "immersion"

    oai_token-act-pair · gpt-3.5-turbo

    references to Pope Benedict

    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
    ãĥ£
    -0.86
    MAG
    -0.82
    claimer
    -0.81
    ports
    -0.70
    Agent
    -0.67
    EAR
    -0.66
    ODUCT
    -0.66
    PLAY
    -0.66
    ©¶æ
    -0.65
    fight
    -0.65
    POSITIVE LOGITS
     Cumber
    1.26
     Benedict
    1.05
    itial
    1.05
     XVI
    1.04
    icts
    0.75
    icum
    0.75
    batch
    0.74
    hetti
    0.73
     Buckingham
    0.72
    umen
    0.72
    Activations Density 0.028%

    No Known Activations