© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27678
    Prev
    Next
    INDEX
    Explanations

    references to flu and influenza-related topics

    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
    386
    +0.16
    0.9%
    376
    +0.13
    0.8%
    162
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.16
    0.01
    78
    +0.13
    0.01
    300
    +0.12
    0.01
    Negative Logits
    efore
    -1.64
     dear
    -1.56
    rapper
    -1.55
    hip
    -1.53
    hips
    -1.48
     distance
    -1.48
    lessly
    -1.46
    atively
    -1.43
    ´
    -1.42
    ward
    -1.42
    POSITIVE LOGITS
    iero
    1.78
     filings
    1.76
    burg
    1.57
    stadt
    1.53
    share
    1.51
    bank
    1.49
    enza
    1.49
    state
    1.48
    idity
    1.48
    ido
    1.48
    Activations Density 1.568%

    No Known Activations