Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 21585
    Prev
    Next
    INDEX
    Explanations

    prayers and expressions related to spiritual faith and accountability

    oai_token-act-pair · gpt-3.5-turbo

    references to divinity and expressions of faith

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    punk
    -0.72
     slides
    -0.71
    inton
    -0.70
    */(
    -0.70
     photoc
    -0.70
     breakdown
    -0.70
     scen
    -0.70
     caric
    -0.68
     stereotyp
    -0.68
     Photograph
    -0.67
    POSITIVE LOGITS
     Almighty
    1.79
     God
    1.41
     GOD
    1.37
     Creator
    1.21
     Blessed
    1.20
     LORD
    1.19
    God
    1.18
     blessed
    1.18
     Allah
    1.17
     Divine
    1.15
    Activations Density 0.280%

    No Known Activations