© 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. 25988
    Prev
    Next
    INDEX
    Explanations

    the word "with" in various contexts

    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
    407
    +0.16
    0.9%
    284
    +0.13
    0.7%
    118
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.16
    0.06
    219
    +0.13
    0.06
    407
    +0.13
    0.06
    Negative Logits
     lightly
    -1.64
     blunt
    -1.62
     reass
    -1.59
     air
    -1.56
     lay
    -1.55
     repeat
    -1.51
     conclude
    -1.49
     quickly
    -1.49
     gently
    -1.48
     promptly
    -1.46
    POSITIVE LOGITS
    »¿
    2.78
    ĥ½
    2.68
    Ļª
    2.66
    <|outofrange|>
    2.56
              ↵
    2.56
     ↵
    2.56
    <|outofrange|>
    2.56
    ↵
    2.56
    ↵
    2.56
    ↵
    2.56
    Activations Density 0.304%

    No Known Activations