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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 7753
    Prev
    Next
    INDEX
    Explanations

    countries and topics related to Cambodia

    oai_token-act-pair · gpt-3.5-turbo

    references to Cambodia and related cultural topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    bow
    -0.88
    igned
    -0.86
    mond
    -0.82
    infeld
    -0.82
    igue
    -0.80
    ipple
    -0.78
    enger
    -0.77
    pec
    -0.76
    vous
    -0.76
    zzle
    -0.76
    POSITIVE LOGITS
    orea
    0.86
     Cambod
    0.80
     bamboo
    0.80
    SourceFile
    0.79
     Cambodia
    0.79
     Kai
    0.76
     Tai
    0.75
    oda
    0.75
     Laos
    0.75
    ication
    0.74
    Activations Density 0.022%

    No Known Activations