© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 20691
    Prev
    Next
    INDEX
    Explanations

    references to sacred or religious entities

    oai_token-act-pair · gpt-3.5-turbo

    references to "Holy" entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.83
    PsyNetMessage
    -0.81
    ickr
    -0.79
    ĸļ
    -0.79
    phrine
    -0.79
    azeera
    -0.74
    yrinth
    -0.72
    DonaldTrump
    -0.71
    atown
    -0.71
    ript
    -0.71
    POSITIVE LOGITS
     Grail
    1.00
     Scripture
    0.85
    father
    0.83
    field
    0.78
     Scriptures
    0.77
     Father
    0.76
     Trinity
    0.74
    house
    0.74
    hearted
    0.72
     Places
    0.72
    Activations Density 0.018%

    No Known Activations