© 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. 11-RES-JB
    11. 22225
    Prev
    Next
    INDEX
    Explanations

    emotions or attitudes related to interpersonal relationships or societal dynamics

    oai_token-act-pair · gpt-3.5-turbo

    themes of trust, understanding, and societal emotions related to governance and community dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dule
    -0.75
    aster
    -0.75
    icles
    -0.71
    icle
    -0.70
    ãĤ´ãĥ³
    -0.69
    leigh
    -0.64
    poon
    -0.63
     bye
    -0.59
     escort
    -0.59
    odore
    -0.58
    POSITIVE LOGITS
     among
    1.50
     amongst
    1.44
    among
    1.29
     within
    1.22
     inside
    1.10
     perv
    1.04
     prevalent
    0.99
     perme
    0.89
    inside
    0.87
     across
    0.87
    Activations Density 0.348%

    No Known Activations