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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27609
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    87
    +0.11
    0.6%
    264
    +0.11
    0.6%
    366
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    264
    +0.11
    0.01
    366
    +0.11
    0.01
    76
    +0.11
    0.01
    Negative Logits
    abbit
    -1.74
     ?"
    -1.66
     etc
    -1.62
     /**<
    -1.60
    anni
    -1.60
    aned
    -1.51
    anus
    -1.48
      ↵
    -1.47
    aten
    -1.44
     Figure
    -1.43
    POSITIVE LOGITS
     submissions
    1.79
    cco
    1.79
     victories
    1.58
    xim
    1.58
    uchy
    1.54
     win
    1.53
    bie
    1.52
    book
    1.46
    otherapy
    1.43
     punches
    1.42
    Activations Density 0.122%

    No Known Activations