© 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. 25884
    Prev
    Next
    INDEX
    Explanations

    elements related to data types and memory management in programming

    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
    23
    +0.15
    0.9%
    90
    +0.15
    0.9%
    42
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.15
    0.03
    343
    +0.15
    0.03
    400
    +0.13
    0.02
    Negative Logits
    -2.43
    ↵
    -2.43
    ↵
    -2.43
    -2.43
    ↵
    -2.43
    -2.43
    ↵↵
    -2.43
    ↵
    -2.43
    -2.43
    ↵
    -2.43
    POSITIVE LOGITS
     Mass
    1.50
    olk
    1.39
     Ton
    1.39
    eren
    1.38
    junction
    1.38
     Ill
    1.37
    ounter
    1.36
     Shadow
    1.35
    lesh
    1.34
     Nic
    1.34
    Activations Density 0.227%

    No Known Activations