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

    Neuronpedia

    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. 11-RES-JB
    11. 22313
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and philosophical or theological terms related to spirituality and belief systems

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to spirituality and higher powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttes
    -0.97
    isons
    -0.86
    anamo
    -0.81
    kees
    -0.80
    ©¶æ
    -0.79
    idelines
    -0.79
    downs
    -0.78
    missions
    -0.78
    shots
    -0.78
    pps
    -0.78
    POSITIVE LOGITS
     deity
    1.51
     creature
    1.47
     entity
    1.47
     organism
    1.35
     thinker
    1.23
     ruler
    1.18
     god
    1.17
     tyrant
    1.16
     embodiment
    1.16
     civilisation
    1.15
    Activations Density 0.329%

    No Known Activations