© 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. 26382
    Prev
    Next
    INDEX
    Explanations

    adjectives indicating emphasis or special attention

    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
    +0.14
    0.8%
    507
    +0.12
    0.7%
    123
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.14
    0.04
    130
    +0.12
    0.04
    123
    +0.12
    0.03
    Negative Logits
     yourself
    -1.53
     mechanically
    -1.42
     helpful
    -1.42
     thoughts
    -1.41
     yourselves
    -1.39
     freely
    -1.38
    ational
    -1.37
     tips
    -1.35
    string
    -1.35
     plenty
    -1.33
    POSITIVE LOGITS
    Ļª
    4.80
     ↵
    4.34
    4.34
     ↵
    4.34
    <|outofrange|>
    4.34
    4.34
    ↵
    4.34
    ↵
    4.34
    ↵
    4.34
    4.34
    Activations Density 0.173%

    No Known Activations