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

    Neuronpedia

    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. 7-RES-JB
    11. 23053
    Prev
    Next
    INDEX
    Explanations

    words related to the hotel chain "Ritz-Carlton"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific name associated with prominent hotels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.76
    selves
    -0.75
    Interstitial
    -0.66
     synonymous
    -0.66
     Pradesh
    -0.65
     NCT
    -0.65
    åŃ
    -0.65
     downstream
    -0.64
     unden
    -0.64
     occas
    -0.63
    POSITIVE LOGITS
    gerald
    1.67
    sch
    1.17
    patrick
    1.13
    heimer
    1.00
    enger
    0.97
    enegger
    0.95
    roth
    0.95
    arella
    0.94
    itz
    0.94
    arro
    0.93
    Activations Density 0.032%

    No Known Activations