© 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. 6492
    Prev
    Next
    INDEX
    Explanations

    words related to deceitful behavior or hidden actions

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "obvious"

    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
     largeDownload
    -0.78
     diplom
    -0.66
     KY
    -0.63
     tempo
    -0.63
     prescribed
    -0.62
     tighter
    -0.62
     quotas
    -0.62
    umm
    -0.61
    Downloadha
    -0.61
     loader
    -0.61
    POSITIVE LOGITS
    vious
    1.31
    nesses
    1.01
    viously
    0.91
    vous
    0.86
    terday
    0.83
    lihood
    0.81
    vier
    0.80
    ness
    0.78
    ãĤ¦ãĤ¹
    0.76
    tenance
    0.74
    Activations Density 0.004%

    No Known Activations