© 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. 2-RES-JB
    11. 3934
    Prev
    Next
    INDEX
    Explanations

    references to weddings

    oai_token-act-pair · gpt-3.5-turbo

    references to weddings and wedding ceremonies

    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
    ulhu
    -0.71
    chie
    -0.69
    anwhile
    -0.68
    osta
    -0.67
    Cola
    -0.67
    pmwiki
    -0.66
    Downloadha
    -0.65
    ussen
    -0.63
    ulz
    -0.63
    OST
    -0.62
    POSITIVE LOGITS
    nesday
    1.17
     wedding
    0.91
    bands
    0.87
     ceremony
    0.84
     chapel
    0.83
     Wedding
    0.82
     weddings
    0.79
     Bride
    0.76
     receptions
    0.75
    glers
    0.73
    Activations Density 0.008%

    No Known Activations