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. 5-RES-JB
    6. 7710
    Prev
    Next
    INDEX
    Explanations

    instances of the term "crossover" and related concepts indicating crossing or merging of different elements or genres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to crossover events or convergent phenomena

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eral
    -0.86
    yd
    -0.78
    estate
    -0.77
    erves
    -0.74
    ulton
    -0.74
    est
    -0.73
    ido
    -0.72
    sb
    -0.72
    ysis
    -0.71
    ĪĴ
    -0.71
    POSITIVE LOGITS
     Consortium
    0.93
    rossover
    0.92
    rosso
    0.88
    inational
    0.83
     crossover
    0.81
     Beir
    0.79
    plex
    0.76
    wake
    0.73
    halla
    0.73
     conver
    0.72
    Activations Density 0.036%

    No Known Activations