© 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. 10-RES-JB
    11. 4694
    Prev
    Next
    INDEX
    Explanations

    words related to social belonging and inclusion

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with inclusion and representation in various communities or organizations

    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
    aeus
    -0.71
    resp
    -0.70
     Delay
    -0.68
    wid
    -0.67
    ynchron
    -0.66
    tip
    -0.65
    moil
    -0.64
    weak
    -0.63
    ................................................................
    -0.61
    rompt
    -0.60
    POSITIVE LOGITS
     society
    1.39
     mainstream
    1.03
     prestigious
    1.02
     civilized
    0.91
     afterlife
    0.87
     elite
    0.86
     future
    0.85
     priesthood
    0.85
    soc
    0.85
    thood
    0.85
    Activations Density 0.399%

    No Known Activations