© 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. 6-RES-JB
    11. 14509
    Prev
    Next
    INDEX
    Explanations

    phrases related to moral judgments and opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the concept of acceptability or unacceptability

    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
    craft
    -0.82
    enfranch
    -0.78
    dream
    -0.77
    ilant
    -0.76
    planes
    -0.76
    ynthesis
    -0.74
    ocket
    -0.72
    wright
    -0.72
    frey
    -0.72
    lets
    -0.72
    POSITIVE LOGITS
     deviations
    0.79
     CPC
    0.72
    ible
    0.71
     standards
    0.71
     Danger
    0.71
     srfAttach
    0.70
    itable
    0.70
     compromises
    0.69
    Gi
    0.69
     norms
    0.69
    Activations Density 0.037%

    No Known Activations