© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24329
    Prev
    Next
    INDEX
    Explanations

    references to valves and maintenance-related terms in technical 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
    271
    +0.15
    0.8%
    476
    +0.13
    0.7%
    497
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.15
    0.09
    478
    +0.13
    0.10
    325
    +0.12
    0.07
    Negative Logits
    owed
    -1.85
    ied
    -1.83
    rely
    -1.76
     replaced
    -1.69
    eous
    -1.64
    iting
    -1.60
     thereon
    -1.58
    ters
    -1.57
    eful
    -1.53
     except
    -1.53
    POSITIVE LOGITS
    ĻĤ
    5.69
    č↵
    5.54
    5.54
     ↵
    5.54
    5.54
    č↵č↵
    5.54
    č↵
    5.54
    ↵
    5.54
    ↵        ↵
    5.54
    <|outofrange|>
    5.54
    Activations Density 1.519%

    No Known Activations