© 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. 3-RES-JB
    11. 12527
    Prev
    Next
    INDEX
    Explanations

    references to religious figures or historical individuals being honored or revered

    oai_token-act-pair · gpt-3.5-turbo

    references to saints and martyrs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    POR
    -0.72
    é¾
    -0.72
    ACA
    -0.71
    PT
    -0.70
    æ©Ł
    -0.67
    ORN
    -0.66
    perm
    -0.65
     NEC
    -0.65
    UST
    -0.64
    addock
    -0.64
    POSITIVE LOGITS
     saint
    0.96
    liness
    0.89
     saints
    0.84
     martyr
    0.83
    esses
    0.80
     healer
    0.78
    âĶĢâĶĢ
    0.73
    lier
    0.70
    iour
    0.70
     heal
    0.67
    Activations Density 0.008%

    No Known Activations