© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18791
    Prev
    Next
    INDEX
    Explanations

    phrases showing empathy, support, or concern for different groups of people

    oai_token-act-pair · gpt-3.5-turbo

    contexts related to global impact and collective consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etting
    -0.82
    oaded
    -0.73
    worn
    -0.71
    Vers
    -0.62
    pmwiki
    -0.62
    illac
    -0.61
    oult
    -0.60
    imilar
    -0.58
     disse
    -0.58
    utenberg
    -0.58
    POSITIVE LOGITS
     humankind
    1.12
     wider
    1.10
     society
    1.04
     mankind
    1.03
     everybody
    1.02
     anybody
    0.97
     everyone
    0.96
     broader
    0.95
     humanity
    0.95
     entire
    0.92
    Activations Density 0.281%

    No Known Activations