© 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
    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. 1258
    Prev
    Next
    INDEX
    Explanations

    terms related to a fictional entity called "SCP-190," particularly focusing on containment procedures and descriptions

    oai_token-act-pair · gpt-3.5-turbo

    details about safety and containment procedures for a specific object or entity

    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
     bund
    -0.97
     endorsements
    -0.90
     benchmark
    -0.89
    ï¸ı
    -0.86
     subsid
    -0.81
    govtrack
    -0.79
     subsidies
    -0.78
     monet
    -0.77
     divor
    -0.77
     golf
    -0.76
    POSITIVE LOGITS
     âĸĪ
    1.48
    SCP
    1.40
     SCP
    1.38
    âĸĪâĸĪâĸĪâĸĪ
    1.29
    âĸĪâĸĪ
    1.26
    REDACTED
    1.16
    âĸĪ
    1.06
    DATA
    0.99
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    0.97
     containment
    0.96
    Activations Density 0.250%

    No Known Activations