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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2095
    Prev
    Next
    INDEX
    Explanations

    phrases related to deception and misinformation

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to misinformation and deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.93
    ktop
    -0.80
    inement
    -0.79
    limits
    -0.76
    adelphia
    -0.73
    unctions
    -0.73
    20439
    -0.73
    uve
    -0.72
    phabet
    -0.72
     Ports
    -0.71
    POSITIVE LOGITS
     fake
    2.05
     hoax
    1.98
     Fake
    1.93
     faked
    1.88
     phony
    1.86
    Fake
    1.86
     false
    1.85
     falsehood
    1.84
     deception
    1.82
     bogus
    1.78
    Activations Density 0.614%

    No Known Activations