© 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. 2-RES-JB
    11. 6307
    Prev
    Next
    INDEX
    Explanations

    words related to superiority or beings considered superior

    oai_token-act-pair · gpt-3.5-turbo

    references to superiority or hierarchy, particularly regarding individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mberg
    -0.95
    BRE
    -0.89
     Dresden
    -0.82
    kj
    -0.80
    gren
    -0.78
    MG
    -0.76
    RPG
    -0.75
    di
    -0.72
    uzz
    -0.71
    qt
    -0.70
    POSITIVE LOGITS
     superior
    0.96
     superiority
    0.88
     dilig
    0.85
     inferior
    0.82
     unbeliev
    0.81
     compliments
    0.80
    intendent
    0.80
     judgement
    0.78
     nomine
    0.77
     insign
    0.77
    Activations Density 0.010%

    No Known Activations