© 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. 3-RES-JB
    11. 21097
    Prev
    Next
    INDEX
    Explanations

    words related to religious or spiritual figures

    oai_token-act-pair · gpt-3.5-turbo

    references to spiritual leaders or gurus

    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
    itional
    -0.67
    shows
    -0.67
    ographs
    -0.65
    turn
    -0.61
    itions
    -0.61
    stros
    -0.61
     Agents
    -0.61
    oslov
    -0.60
    ellen
    -0.60
    orum
    -0.59
    POSITIVE LOGITS
    uru
    1.14
    hod
    1.06
    geon
    0.96
    umbai
    0.94
    vana
    0.91
    isoft
    0.85
    yu
    0.83
    jee
    0.79
    isu
    0.78
    zzo
    0.78
    Activations Density 0.014%

    No Known Activations