© 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. 4-RES-JB
    11. 14774
    Prev
    Next
    INDEX
    Explanations

    references to individuals with royal titles, particularly 'King'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of royalty, specifically references to kings

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

    No Comments

    Negative Logits
    eria
    -0.79
    TING
    -0.75
    uated
    -0.74
    ename
    -0.73
    ciplinary
    -0.72
    ters
    -0.71
    ATIONAL
    -0.68
    Availability
    -0.68
    Ñı
    -0.67
    utic
    -0.67
    POSITIVE LOGITS
    pin
    1.21
    uin
    1.14
    dom
    1.13
    doms
    1.12
    pins
    1.06
    fish
    1.01
    DOM
    1.00
    lord
    0.91
    STON
    0.90
    killer
    0.89
    Activations Density 0.015%

    No Known Activations