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. 1-RES-JB
    6. 12085
    Prev
    Next
    INDEX
    Explanations

    references to the concept of heaven

    oai_token-act-pair · gpt-3.5-turbo

    references to 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 @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VICE
    -0.82
    Thom
    -0.81
    owicz
    -0.80
    Published
    -0.78
    Hyper
    -0.78
    DATA
    -0.75
    JUST
    -0.73
    Technical
    -0.73
    Medical
    -0.73
    Accessory
    -0.72
    POSITIVE LOGITS
     heaven
    1.10
     forbid
    0.97
     heavenly
    0.92
     Heaven
    0.91
    urous
    0.91
    adelphia
    0.91
     paradise
    0.91
    ruciating
    0.87
     tremend
    0.83
     bless
    0.81
    Activations Density 0.006%

    No Known Activations