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. 319
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations on Earth

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote various geographical entities or regions

    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
    olson
    -0.74
     Cly
    -0.74
    govtrack
    -0.74
    staking
    -0.71
    utenant
    -0.71
    thood
    -0.69
    minecraft
    -0.65
     Marketable
    -0.64
    ufact
    -0.64
    verett
    -0.63
    POSITIVE LOGITS
     periphery
    0.86
     globe
    0.84
     seams
    0.79
     perimeter
    0.78
     corners
    0.77
     corner
    0.76
     edges
    0.75
    clock
    0.72
    士
    0.70
     denomination
    0.69
    Activations Density 0.102%

    No Known Activations