© 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. 10-RES-JB
    11. 17347
    Prev
    Next
    INDEX
    Explanations

    information related to paranormal phenomena and conspiracy theories

    oai_token-act-pair · gpt-3.5-turbo

    references to paranormal investigations and associated phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -1.00
    Iv
    -0.93
    estyle
    -0.89
    ļéĨĴ
    -0.89
    Wallet
    -0.86
    offset
    -0.85
     Barclays
    -0.84
    ettel
    -0.84
    ilage
    -0.83
    lane
    -0.82
    POSITIVE LOGITS
     paranormal
    1.81
     UFOs
    1.79
     UFO
    1.77
     Lovecraft
    1.65
     occult
    1.64
     Cthulhu
    1.62
     supernatural
    1.57
     hallucinations
    1.56
     demonic
    1.48
     halluc
    1.46
    Activations Density 0.569%

    No Known Activations