© 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. 0-MLP-SM
    11. 27734
    Prev
    Next
    INDEX
    Explanations

    negative or null indicators in code or technical texts

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    121
    +0.15
    0.8%
    355
    +0.14
    0.8%
    99
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.15
    0.20
    316
    +0.14
    0.18
    390
    +0.12
    0.18
    Negative Logits
     walks
    -1.60
    lessly
    -1.54
     unlocked
    -1.53
     marketplace
    -1.53
     refrigerator
    -1.47
     fut
    -1.36
     mirrors
    -1.35
     fridge
    -1.32
     walk
    -1.30
    bracket
    -1.27
    POSITIVE LOGITS
    Ĩ
    2.21
    ¿½
    2.12
    ·¸
    2.05
    Į
    1.89
    ķ
    1.87
    Ŀ
    1.78
    ĨĴ
    1.70
    ¿
    1.68
    ı
    1.64
    ¾
    1.59
    Activations Density 0.821%

    No Known Activations