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. 27641
    Prev
    Next
    INDEX
    Explanations

    the mention of musical groups characterized as duos or trios

    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
    156
    +0.17
    1.0%
    376
    +0.17
    1.0%
    487
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.17
    0.01
    487
    +0.17
    0.01
    329
    +0.12
    0.01
    Negative Logits
     helping
    -1.46
    rapy
    -1.46
    ____________
    -1.46
     advice
    -1.42
     Copyright
    -1.42
     Youth
    -1.39
     wonderful
    -1.37
     dignity
    -1.36
     youth
    -1.35
    YLE
    -1.35
    POSITIVE LOGITS
    gres
    1.86
    agem
    1.82
    chin
    1.80
    het
    1.75
    erals
    1.70
    nal
    1.69
    edin
    1.69
    cript
    1.68
    aje
    1.68
    stown
    1.68
    Activations Density 0.016%

    No Known Activations