© 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. 4-RES-JB
    11. 7475
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of the truth or critical assessment of situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lie" and its variations, indicating discussions of hidden truths or deceptions

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

    No Comments

    Negative Logits
    aldi
    -0.81
    aud
    -0.79
    obs
    -0.75
    iles
    -0.71
    ilar
    -0.69
    smart
    -0.68
    ains
    -0.66
    inky
    -0.66
    ISO
    -0.65
    ilic
    -0.64
    POSITIVE LOGITS
    uten
    0.95
    utenant
    0.82
     detector
    0.81
    lie
    0.79
     Lies
    0.77
     dormant
    0.72
     vulner
    0.72
     Reincarn
    0.71
     lie
    0.67
    ppe
    0.66
    Activations Density 0.011%

    No Known Activations