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. 8-RES-JB
    6. 20722
    Prev
    Next
    INDEX
    Explanations

    references to mythical or magical objects, creatures, or concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mythology and magical elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Startup
    -0.93
     DSM
    -0.87
    Bernie
    -0.82
    Dispatch
    -0.81
    STD
    -0.79
     Reviews
    -0.78
     Expand
    -0.78
     Comcast
    -0.78
     SOFTWARE
    -0.77
    Metro
    -0.77
    POSITIVE LOGITS
     ceremonial
    1.31
     ceremon
    1.17
     deity
    1.13
     ritual
    1.11
     sacred
    1.09
     consec
    1.09
     crucifix
    1.06
     goddess
    1.05
     ceremonies
    1.05
     divine
    1.03
    Activations Density 0.832%

    No Known Activations