© 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. 8-RES-JB
    11. 113
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "queue"

    oai_token-act-pair · gpt-3.5-turbo

    references to queer identities and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inating
    -0.80
    inately
    -0.80
    iaries
    -0.75
    lessly
    -0.73
    ERSON
    -0.71
    appers
    -0.69
    uania
    -0.69
    izont
    -0.68
    iary
    -0.68
    iband
    -0.67
    POSITIVE LOGITS
    que
    0.97
    odore
    0.87
    edo
    0.87
    erness
    0.79
    zon
    0.76
    zzi
    0.75
    ño
    0.75
    ague
    0.74
     Patriarch
    0.73
    enne
    0.73
    Activations Density 0.033%

    No Known Activations