© 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. 2-RES-JB
    11. 16341
    Prev
    Next
    INDEX
    Explanations

    phrases related to hospitality or welcoming guests

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "guests."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skydragon
    -0.67
    legraph
    -0.64
     Rite
    -0.64
    66666666
    -0.64
    sis
    -0.62
     Decay
    -0.60
     Shotgun
    -0.60
     Campaign
    -0.59
     Ecology
    -0.58
    nces
    -0.58
    POSITIVE LOGITS
     guests
    1.27
     Guests
    1.11
     guest
    0.87
    esses
    0.85
    hip
    0.82
    DragonMagazine
    0.81
    cript
    0.80
     attractions
    0.77
    maid
    0.77
    Tickets
    0.76
    Activations Density 0.009%

    No Known Activations