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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 1099
    Prev
    Next
    INDEX
    Explanations

    words related to spirituality or divinity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the divine or spiritual concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akeru
    -0.97
    skirts
    -0.93
    arf
    -0.89
     Lans
    -0.87
    laus
    -0.86
    WAR
    -0.81
    Downloadha
    -0.78
    PsyNetMessage
    -0.78
    cro
    -0.75
     Loaded
    -0.72
    POSITIVE LOGITS
     decree
    0.96
     beings
    0.91
     feminine
    0.90
     rays
    0.89
     divine
    0.86
    ly
    0.86
     blessing
    0.85
     energies
    0.85
     retribution
    0.84
     blessings
    0.81
    Activations Density 0.010%

    No Known Activations