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. 0-RES-JB
    6. 14038
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "Ecuador"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Ecuador

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spartan
    -0.73
    Battle
    -0.71
    orie
    -0.70
     Spartans
    -0.69
     ///
    -0.66
     roadside
    -0.65
     Sack
    -0.64
     uniforms
    -0.64
     drives
    -0.64
    ipeg
    -0.63
    POSITIVE LOGITS
     Ecuador
    3.68
    uador
    2.24
    Ec
    1.71
     Zub
    1.57
     Chevron
    1.29
     Ec
    1.29
     Assange
    1.19
     extrad
    1.19
     Argentine
    1.17
     Urug
    1.16
    Activations Density 0.036%

    No Known Activations