© 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. 2-RES-JB
    11. 23631
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to clear and evident wrongdoing or deception

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blatant" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulton
    -0.93
    oult
    -0.76
    erves
    -0.76
    encers
    -0.75
    ather
    -0.73
    ovember
    -0.72
    arios
    -0.72
     safely
    -0.72
    adal
    -0.70
    agine
    -0.70
    POSITIVE LOGITS
    iary
    0.88
     violation
    0.86
     misrepresent
    0.84
     violations
    0.82
     blatant
    0.79
     blatantly
    0.79
     disregard
    0.78
     hypocrisy
    0.77
     contradiction
    0.76
     glaring
    0.76
    Activations Density 0.020%

    No Known Activations