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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2805
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "demon" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to demons in various contexts

    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
    ictionary
    -0.75
     McK
    -0.74
    itably
    -0.72
     overw
    -0.69
     airlines
    -0.68
     parenting
    -0.65
     padd
    -0.64
    IPP
    -0.64
     lett
    -0.64
    olson
    -0.64
    POSITIVE LOGITS
     Demon
    3.87
    Demon
    3.46
    demon
    2.53
     Demons
    1.82
     Demonic
    1.55
     Chaos
    1.32
     demon
    1.25
     DEM
    1.21
     Demo
    1.18
    DEM
    1.18
    Activations Density 0.018%

    No Known Activations