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. 10307
    Prev
    Next
    INDEX
    Explanations

    countries or cities that people might travel to

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical locations or cities associated with travel

    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
     resemblance
    -0.60
     compared
    -0.59
     indicators
    -0.59
    sbm
    -0.58
     resemb
    -0.58
     quantity
    -0.57
     Trend
    -0.57
     nods
    -0.56
    vich
    -0.55
     pie
    -0.55
    POSITIVE LOGITS
     shores
    0.89
     destinations
    0.82
     docks
    0.79
     via
    0.79
    livion
    0.78
     Harbour
    0.75
     coffers
    0.74
    venge
    0.74
     fray
    0.73
     sidelines
    0.72
    Activations Density 0.323%

    No Known Activations