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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 16620
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations or coordinates, specifically those related to "Lat"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Lat" and its variations, suggesting a focus on geographical or political references related to Latin regions or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®éŃĶ
    -0.79
    EMENT
    -0.75
    OHN
    -0.75
    éĹĺ
    -0.72
    CRIP
    -0.71
    LEASE
    -0.71
    ushima
    -0.71
    ãģį
    -0.70
    vironment
    -0.70
    æĸ¹
    -0.69
    POSITIVE LOGITS
    itude
    1.09
    itud
    0.96
    ency
    0.95
     Lat
    0.95
    itudes
    0.87
    akia
    0.85
    imes
    0.85
    itudinal
    0.84
    lat
    0.83
    robe
    0.80
    Activations Density 0.008%

    No Known Activations