© 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. 10-RES-JB
    11. 16134
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of hidden or underlying truths or factors

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "lying" or "situating."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivals
    -0.68
     minded
    -0.62
    haw
    -0.61
    aga
    -0.59
    alth
    -0.59
     frenzy
    -0.58
    eer
    -0.57
    agers
    -0.56
     Marriott
    -0.55
    panic
    -0.55
    POSITIVE LOGITS
     squarely
    1.12
     dormant
    1.10
     somewhere
    1.05
     beneath
    1.02
     behind
    1.00
    behind
    0.94
    hidden
    0.87
     within
    0.87
     outside
    0.85
     underneath
    0.84
    Activations Density 0.062%

    No Known Activations