© 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. 1-RES-JB
    11. 20221
    Prev
    Next
    INDEX
    Explanations

    words related to moral or personal virtues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to morality and virtue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ockets
    -0.82
    oval
    -0.71
    bered
    -0.67
    grown
    -0.67
    ZI
    -0.65
    alone
    -0.61
    gren
    -0.61
     fragmented
    -0.60
    cedented
    -0.60
    KS
    -0.60
    POSITIVE LOGITS
     virtue
    1.02
     signalling
    0.93
     Virtue
    0.88
     dilig
    0.83
     signaling
    0.80
    iosity
    0.78
     Deity
    0.76
    ienne
    0.76
     distingu
    0.75
     resil
    0.73
    Activations Density 0.007%

    No Known Activations