© 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. 2-RES-JB
    11. 3974
    Prev
    Next
    INDEX
    Explanations

    words related to unethical behavior or wrongdoings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "misconduct" in various contexts

    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
    izen
    -0.72
    stanbul
    -0.69
     Sabha
    -0.67
    etically
    -0.67
    imb
    -0.67
    frey
    -0.66
    bern
    -0.66
    zyme
    -0.66
    iku
    -0.66
    kos
    -0.65
    POSITIVE LOGITS
     misconduct
    1.26
    onduct
    1.10
     allegations
    0.94
     malf
    0.94
     abuses
    0.88
     wrongdoing
    0.85
     unfocusedRange
    0.85
     disclosures
    0.81
     violations
    0.80
     scandals
    0.79
    Activations Density 0.010%

    No Known Activations