© 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. 1-RES-JB
    11. 15785
    Prev
    Next
    INDEX
    Explanations

    words related to faith or belief

    oai_token-act-pair · gpt-3.5-turbo

    mentions of infidelity and unfaithfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bett
    -0.83
     Gloves
    -0.71
     Roz
    -0.67
     goggles
    -0.67
    taboola
    -0.67
     Rasm
    -0.65
     Klaus
    -0.64
     Papers
    -0.63
     Mouse
    -0.63
    ATA
    -0.62
    POSITIVE LOGITS
    vironment
    1.13
    ryu
    0.92
    akespeare
    0.91
    peror
    0.85
    olitics
    0.85
    abol
    0.84
    xual
    0.84
    uncture
    0.83
    metics
    0.80
    stall
    0.80
    Activations Density 0.040%

    No Known Activations