© 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. 27765
    Prev
    Next
    INDEX
    Explanations

    references to environmental protection agencies

    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
    +0.20
    1.2%
    219
    +0.13
    0.8%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.20
    0.01
    219
    +0.13
    0.01
    105
    +0.12
    0.01
    Negative Logits
     anybody
    -1.88
     anyone
    -1.76
     yours
    -1.76
     why
    -1.65
     ever
    -1.64
     anything
    -1.62
     faire
    -1.61
     your
    -1.61
     stranger
    -1.59
     somebody
    -1.56
    POSITIVE LOGITS
    »¿
    1.94
    ģ
    1.91
    iom
    1.80
    opan
    1.71
    epi
    1.62
    °
    1.61
    head
    1.61
    ilee
    1.57
    ctions
    1.55
    ios
    1.54
    Activations Density 0.017%

    No Known Activations