© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 22299
    Prev
    Next
    INDEX
    Explanations

    phrases related to different forms of lying

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lie" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     connecting
    -0.65
     pip
    -0.63
     access
    -0.61
     Vital
    -0.60
     tabs
    -0.59
     rounded
    -0.59
     stats
    -0.59
     pool
    -0.59
     upgraded
    -0.59
     scheduled
    -0.59
    POSITIVE LOGITS
    lie
    5.00
    lies
    2.16
    Lie
    1.66
    lied
    1.46
    lia
    1.44
    lio
    1.43
    li
    1.42
     Lie
    1.39
    lying
    1.23
    leigh
    1.19
    Activations Density 0.011%

    No Known Activations