© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 7676
    Prev
    Next
    INDEX
    Explanations

    mentions of mythical creatures or supernatural entities

    oai_token-act-pair · gpt-3.5-turbo

    elements related to supernatural themes and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Casual
    -0.77
     Competitive
    -0.73
    baugh
    -0.72
    orters
    -0.72
     Accuracy
    -0.71
    backer
    -0.68
     Playoff
    -0.66
    professional
    -0.66
     Savings
    -0.66
     Cheap
    -0.65
    POSITIVE LOGITS
     inhab
    1.34
     haunting
    1.31
     haun
    1.27
     beck
    1.27
     incarn
    1.21
     haunt
    1.21
     prophes
    1.17
     dwell
    1.15
     lurking
    1.14
     worshipped
    1.14
    Activations Density 0.430%

    No Known Activations