© 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. 7-RES-JB
    11. 23821
    Prev
    Next
    INDEX
    Explanations

    words related to societal norms and cultural beliefs

    oai_token-act-pair · gpt-3.5-turbo

    references to societal norms and cultural practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ded
    -0.71
    ש
    -0.69
    aman
    -0.68
    amen
    -0.68
    MER
    -0.68
    onement
    -0.68
    Interstitial
    -0.67
    amaz
    -0.66
    CLASSIFIED
    -0.66
    ×ŀ
    -0.65
    POSITIVE LOGITS
    ystem
    1.11
    pace
    1.02
    pring
    1.02
    cape
    1.01
    omething
    1.00
    mith
    0.99
     affecting
    0.96
    hops
    0.95
    hip
    0.92
     influencing
    0.89
    Activations Density 0.276%

    No Known Activations