© 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. 25904
    Prev
    Next
    INDEX
    Explanations

    the word "here" 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
    76
    +0.18
    1.0%
    424
    +0.14
    0.8%
    481
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.18
    0.04
    424
    +0.14
    0.03
    184
    +0.13
    0.02
    Negative Logits
    ↵
    -3.66
    <|outofrange|>
    -3.66
    ↵
    -3.66
    ↵            ↵
    -3.66
    <|outofrange|>
    -3.66
    -3.66
    ↵
    -3.66
    ↵  ↵
    -3.66
              ↵
    -3.66
    č↵
    -3.66
    POSITIVE LOGITS
    ]{.
    1.60
     tam
    1.59
     ''
    1.54
    [@
    1.46
     mode
    1.45
    âĢĬ
    1.42
     vessel
    1.38
     $<$
    1.37
     downs
    1.37
    iscus
    1.35
    Activations Density 0.105%

    No Known Activations