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. 19274
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations in Southeast Asia

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Southeast Asia" and related geographical references

    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
    balls
    -0.83
     Braun
    -0.73
    bid
    -0.70
    abase
    -0.68
     Telesc
    -0.68
    tz
    -0.68
    rera
    -0.67
     GIF
    -0.66
    houses
    -0.66
    ball
    -0.65
    POSITIVE LOGITS
     Asian
    0.95
     Asia
    0.92
    angular
    0.90
    outheast
    0.88
     Asians
    0.86
     Southeast
    0.81
    Asian
    0.80
    Ħ¢
    0.79
    mental
    0.77
     ende
    0.76
    Activations Density 0.021%

    No Known Activations