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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12057
    Prev
    Next
    INDEX
    Explanations

    phrases related to spirituality and deep philosophical concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to spirituality and the collective experience of humanity

    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
    taboola
    -0.93
    ovember
    -0.91
    UNCH
    -0.73
    addons
    -0.72
    ç«
    -0.72
    Ire
    -0.72
    Els
    -0.67
    sbm
    -0.66
    DAQ
    -0.66
    Todd
    -0.66
    POSITIVE LOGITS
     philosophers
    0.87
     truths
    0.85
     Sorce
    0.82
     precept
    0.82
     Virtue
    0.81
     unto
    0.81
     Philos
    0.80
     insepar
    0.79
     doctrines
    0.79
     pleasures
    0.79
    Activations Density 0.777%

    No Known Activations