Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 2530
    Prev
    Next
    INDEX
    Explanations

    phrases related to honesty and ethical behavior

    oai_token-act-pair · gpt-3.5-turbo

    mentions of integrity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opa
    -0.70
    sg
    -0.68
    enegger
    -0.68
    Advertisements
    -0.68
    Stock
    -0.68
    Adapter
    -0.66
    Jet
    -0.66
    Pain
    -0.65
    hop
    -0.65
    Ingredients
    -0.65
    POSITIVE LOGITS
    rity
    1.23
     integrity
    1.19
     Integrity
    1.00
    acies
    0.95
    orously
    0.87
    ulence
    0.84
     safeguards
    0.77
    otiation
    0.77
    amental
    0.77
     preservation
    0.76
    Activations Density 0.009%

    No Known Activations