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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 25418
    Prev
    Next
    INDEX
    Explanations

    references to nodes in a network or tree structure

    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
    +0.28
    1.6%
    198
    +0.12
    0.7%
    333
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.28
    0.03
    198
    +0.12
    0.04
    56
    +0.11
    0.04
    Negative Logits
     meets
    -1.78
     referendum
    -1.71
     constituency
    -1.64
     MLS
    -1.60
     Janeiro
    -1.57
    uary
    -1.53
     FIFA
    -1.53
     during
    -1.52
     election
    -1.47
    ensis
    -1.47
    POSITIVE LOGITS
    equ
    1.77
    }.$
    1.75
    |$.
    1.75
    },$
    1.68
     Sachs
    1.66
    STEM
    1.66
    Thom
    1.64
    bigr
    1.62
    thin
    1.59
    }$.
    1.58
    Activations Density 0.284%

    No Known Activations