© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27686
    Prev
    Next
    INDEX
    Explanations

    mentions of battery-related terms

    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
    64
    +0.12
    0.6%
    303
    +0.12
    0.6%
    475
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.12
    0.02
    82
    +0.12
    0.02
    234
    +0.11
    0.02
    Negative Logits
     goal
    -1.79
     preliminary
    -1.72
     facility
    -1.72
    ters
    -1.69
     habitat
    -1.60
     system
    -1.60
     mitigation
    -1.59
     goodbye
    -1.56
     if
    -1.50
     management
    -1.50
    POSITIVE LOGITS
    ¤
    2.67
    ĺ
    2.61
    Ľ
    2.58
    Ĥ
    2.58
    ĻĤ
    2.46
    ĸ
    2.45
    ©
    2.39
    ¸
    2.31
    ±
    2.31
    Ļª
    2.29
    Activations Density 0.004%

    No Known Activations