© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20035
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "othering."

    oai_token-act-pair · gpt-3.5-turbo

    the term "other" or variations and mentions of Google

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edded
    -0.72
    noon
    -0.66
    lished
    -0.65
     elig
    -0.65
    yrinth
    -0.64
     stacked
    -0.64
    ials
    -0.63
    ially
    -0.63
     consisted
    -0.62
     zero
    -0.62
    POSITIVE LOGITS
    othe
    1.32
    otle
    0.88
    phe
    0.88
    zyme
    0.84
    ogle
    0.80
    azy
    0.78
    ogi
    0.77
    ocal
    0.77
    osit
    0.75
    ãĥĥãĥĪ
    0.75
    Activations Density 0.012%

    No Known Activations