© 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. 1-RES-JB
    11. 24141
    Prev
    Next
    INDEX
    Explanations

    religious or spiritual references and teachings

    oai_token-act-pair · gpt-3.5-turbo

    references to religious concepts and spiritual beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odcast
    -0.90
     CV
    -0.85
    taboola
    -0.83
     Motorola
    -0.80
     CPC
    -0.78
    assic
    -0.76
    Enlarge
    -0.74
    ansky
    -0.74
     NR
    -0.73
    park
    -0.72
    POSITIVE LOGITS
     nob
    1.00
     wrath
    0.95
     thence
    0.95
     heavens
    0.93
     beasts
    0.91
     barbar
    0.91
     hath
    0.90
     whence
    0.90
     heavenly
    0.87
     righteousness
    0.87
    Activations Density 1.507%

    No Known Activations