© 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. 3-RES-JB
    11. 23064
    Prev
    Next
    INDEX
    Explanations

    terms related to societal issues such as diversity, compassion, guilt, and specific societal groups like Republicans or white men

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and emotions

    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
    acket
    -0.55
    ggle
    -0.52
     nutshell
    -0.50
    Newsletter
    -0.47
    election
    -0.47
    Reply
    -0.47
    Ö
    -0.46
     lockout
    -0.46
    {{
    -0.45
    awar
    -0.45
    POSITIVE LOGITS
     notwithstanding
    0.53
    ãĥ³ãĤ¸
    0.53
    wise
    0.49
    =]
    0.46
    aila
    0.45
    ='
    0.44
    ãĥ¥
    0.44
    conservancy
    0.44
    ardless
    0.44
    icultural
    0.44
    Activations Density 1.606%

    No Known Activations