© 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. 26393
    Prev
    Next
    INDEX
    Explanations

    references to surgical procedures and techniques

    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
    +0.14
    0.8%
    496
    +0.13
    0.7%
    413
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.14
    0.01
    160
    +0.13
    0.01
    31
    +0.13
    0.01
    Negative Logits
     whom
    -1.52
    urb
    -1.51
    arium
    -1.49
    encies
    -1.41
    arias
    -1.41
    aria
    -1.40
    hold
    -1.40
    nae
    -1.39
    ques
    -1.39
     borough
    -1.38
    POSITIVE LOGITS
     %.
    1.48
     agg
    1.48
     pleading
    1.45
     fond
    1.38
     thereto
    1.33
     ??
    1.31
     /*!<
    1.29
     </
    1.29
    gered
    1.27
    ↵↵
    1.26
    Activations Density 0.098%

    No Known Activations