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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14979
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to a specific individual or entity named "Snopes"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Snopes," indicating a focus on fact-checking or debunking misinformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.75
     PowerPoint
    -0.74
    heid
    -0.73
    TAIN
    -0.71
     Sunni
    -0.70
     secrecy
    -0.69
    66666666
    -0.67
     Hezbollah
    -0.66
    upon
    -0.65
     PRESS
    -0.64
    POSITIVE LOGITS
    akes
    1.03
    ety
    1.02
    icket
    1.01
    agging
    1.01
    ook
    1.00
    ugg
    1.00
    agged
    0.97
    uggle
    0.97
    iness
    0.96
    ipp
    0.96
    Activations Density 0.010%

    No Known Activations