© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20665
    Prev
    Next
    INDEX
    Explanations

    phrases related to various societal issues or problems

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss various issues impacting society

    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
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.76
    Catalog
    -0.74
    ername
    -0.71
    ffen
    -0.69
    âĹ¼
    -0.68
    rites
    -0.68
    âķIJâķIJ
    -0.66
    gian
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    CBC
    -0.64
    POSITIVE LOGITS
     whether
    1.00
     legality
    0.89
     fairness
    0.84
     homelessness
    0.84
     affordability
    0.80
     homosexuality
    0.76
     protecting
    0.74
     needing
    0.74
     sexuality
    0.72
    equality
    0.72
    Activations Density 0.087%

    No Known Activations