© 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. 6-RES-JB
    11. 15013
    Prev
    Next
    INDEX
    Explanations

    references to unethical behavior, specifically cheating

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cheating and dishonest behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ŃĶ
    -0.74
    Vert
    -0.73
    oan
    -0.69
    00200000
    -0.66
    Pain
    -0.66
    escal
    -0.63
    Cloud
    -0.63
    cept
    -0.63
    ItemThumbnailImage
    -0.62
    arger
    -0.61
    POSITIVE LOGITS
     cheating
    0.86
     cheat
    0.81
    ulative
    0.79
    herer
    0.76
     sheet
    0.68
     cheated
    0.65
    hard
    0.64
     behavior
    0.63
    cheat
    0.63
    yre
    0.61
    Activations Density 0.026%

    No Known Activations