© 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. 4-RES-JB
    11. 10309
    Prev
    Next
    INDEX
    Explanations

    phrases related to preaching and teachings, especially in a religious context

    oai_token-act-pair · gpt-3.5-turbo

    words associated with religious preaching and teachings

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

    No Comments

    Negative Logits
    rin
    -0.67
     Rost
    -0.66
    tw
    -0.65
     NP
    -0.63
    berman
    -0.61
    \/\/
    -0.61
    ARDS
    -0.60
    zanne
    -0.60
     Rue
    -0.60
    fur
    -0.59
    POSITIVE LOGITS
     preached
    1.46
     preaching
    1.11
     preach
    1.04
    hovah
    0.99
    iscopal
    0.91
     loudly
    0.86
    olate
    0.86
     sermon
    0.85
     evangel
    0.78
     tremend
    0.77
    Activations Density 0.029%

    No Known Activations