© 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. 9-RES-JB
    11. 14708
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to kingdoms

    oai_token-act-pair · gpt-3.5-turbo

    references to kingdoms, their characteristics, and royal themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Feed
    -0.81
     Haas
    -0.79
    POS
    -0.75
    iker
    -0.72
     Robo
    -0.71
     Cosponsors
    -0.71
     Participant
    -0.70
     Volunte
    -0.70
    Bay
    -0.70
     Survivors
    -0.69
    POSITIVE LOGITS
    DOM
    1.01
     throne
    0.93
     princes
    0.93
     palace
    0.92
    doms
    0.90
     prince
    0.89
     jewels
    0.86
     kingdoms
    0.84
     kingdom
    0.84
     Halls
    0.83
    Activations Density 0.073%

    No Known Activations