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. 27441
    Prev
    Next
    INDEX
    Explanations

    references to the number of pages

    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
    466
    +0.12
    0.8%
    355
    +0.11
    0.7%
    241
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.12
    0.01
    466
    +0.11
    0.01
    255
    +0.11
    0.01
    Negative Logits
    rians
    -2.18
    trim
    -1.89
    rian
    -1.85
    omitempty
    -1.78
     silence
    -1.72
    matically
    -1.72
     '</
    -1.69
     yours
    -1.69
     fair
    -1.69
     harmless
    -1.61
    POSITIVE LOGITS
    helf
    2.54
    ystems
    1.99
    chaft
    1.92
    ugu
    1.84
    fel
    1.83
    ist
    1.82
    cule
    1.80
    ource
    1.78
    mith
    1.77
    fors
    1.75
    Activations Density 0.011%

    No Known Activations