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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 21472
    Prev
    Next
    INDEX
    Explanations

    the concept of 'heaven'

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with the concept of heaven and the afterlife

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipes
    -0.70
    registered
    -0.64
    raw
    -0.62
     Advertisement
    -0.62
    AY
    -0.61
     Payments
    -0.60
    lection
    -0.60
    rator
    -0.60
    Computer
    -0.59
    Scan
    -0.59
    POSITIVE LOGITS
     heaven
    4.07
     Heaven
    3.35
     heavens
    2.51
     paradise
    2.15
     heavenly
    1.85
     eternity
    1.59
     hell
    1.57
     Purg
    1.53
     Heavenly
    1.51
     afterlife
    1.50
    Activations Density 0.022%

    No Known Activations