Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 14545
    Prev
    Next
    INDEX
    Explanations

    mentions of weddings and related events like ceremonies and receptions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms associated with weddings and wedding-related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ridges
    -0.78
    ritis
    -0.74
    esian
    -0.73
     Classification
    -0.72
    esm
    -0.71
    ike
    -0.70
    obo
    -0.69
    tered
    -0.69
    staking
    -0.67
    é¾
    -0.66
    POSITIVE LOGITS
     reception
    1.13
     gown
    1.05
     receptions
    1.04
     banquet
    1.01
     procession
    1.01
     chapel
    0.97
     party
    0.94
     cake
    0.94
     feast
    0.94
     ceremony
    0.92
    Activations Density 0.072%

    No Known Activations