© 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. 10-RES-JB
    11. 11644
    Prev
    Next
    INDEX
    Explanations

    phrases related to distraction or covering up potential issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to distraction techniques or obfuscation strategies

    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
    romy
    -0.80
     varies
    -0.71
    ®,
    -0.70
    throp
    -0.67
    azes
    -0.66
    uties
    -0.66
    rones
    -0.65
    cients
    -0.65
     molded
    -0.65
    FTWARE
    -0.64
    POSITIVE LOGITS
     publicity
    1.28
     embarrassing
    1.14
     embarrassment
    1.12
     retribution
    1.01
     retaliation
    0.98
     incrim
    0.95
     discredit
    0.94
     embarrass
    0.94
     scapego
    0.88
     retali
    0.87
    Activations Density 0.743%

    No Known Activations