© 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. 2-MLP-SM
    11. 25937
    Prev
    Next
    INDEX
    Explanations

    terms related to cardiovascular and dental health

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.40
    2.4%
    181
    +0.14
    0.8%
    23
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.40
    0.06
    491
    +0.14
    0.05
    181
    +0.13
    0.07
    Negative Logits
    ↵
    -4.89
    ↵↵
    -4.89
    ↵
    -4.89
    <|outofrange|>
    -4.89
    ↵
    -4.89
     ↵
    -4.89
    č↵
    -4.89
                  ↵
    -4.89
              ↵
    -4.89
    -4.89
    POSITIVE LOGITS
     (_
    1.45
    ↵
    1.39
     Darwin
    1.38
    ↵
    1.32
     laid
    1.31
    filling
    1.31
     commenced
    1.29
     Unix
    1.29
    hered
    1.29
    renew
    1.29
    Activations Density 0.505%

    No Known Activations