© 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. 10-RES-JB
    11. 14098
    Prev
    Next
    INDEX
    Explanations

    phrases related to dishonesty and deception

    oai_token-act-pair · gpt-3.5-turbo

    references to dishonesty and deception in political discourse

    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
    agos
    -0.95
    lear
    -0.85
    AMI
    -0.79
     Pets
    -0.78
    illin
    -0.76
    rieve
    -0.76
    plates
    -0.74
    ipeg
    -0.72
    uve
    -0.72
     Waves
    -0.72
    POSITIVE LOGITS
     misrepresent
    1.65
     deceit
    1.57
     misinformation
    1.56
     disinformation
    1.53
     incompetence
    1.49
     deception
    1.49
     misleading
    1.47
     fraud
    1.45
     falsehood
    1.45
     ignorance
    1.44
    Activations Density 0.364%

    No Known Activations