© 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. 2-RES-JB
    11. 13607
    Prev
    Next
    INDEX
    Explanations

    terms related to deception or dishonesty

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the prefix "fe."

    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
     Shining
    -0.71
    ova
    -0.66
     Salvation
    -0.66
    externalActionCode
    -0.65
    displayText
    -0.64
    uyomi
    -0.63
    asking
    -0.63
    owsky
    -0.63
     Crunch
    -0.63
     Authority
    -0.62
    POSITIVE LOGITS
    ldom
    1.08
    encing
    0.93
     fe
    0.93
    ences
    0.91
    vered
    0.89
    eling
    0.86
    ete
    0.86
    ewitness
    0.85
    ld
    0.82
    alty
    0.81
    Activations Density 0.006%

    No Known Activations