© 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. 23117
    Prev
    Next
    INDEX
    Explanations

    sequences of arithmetic expressions or mathematical operations

    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
    269
    +0.13
    0.7%
    336
    +0.12
    0.7%
    92
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.13
    0.02
    336
    +0.12
    0.03
    103
    +0.12
    0.02
    Negative Logits
    ]{.
    -1.96
     hypotheses
    -1.69
    ]:
    -1.63
    opo
    -1.58
    ]\\
    -1.55
    ].$$
    -1.50
    ']
    -1.49
    otry
    -1.47
     omitted
    -1.45
     hypothesis
    -1.41
    POSITIVE LOGITS
    ↵
    4.59
    ↵
    4.59
     ↵
    4.59
    ↵
    4.59
    4.59
    4.59
    4.59
    4.59
       ↵
    4.59
    <|outofrange|>
    4.59
    Activations Density 0.118%

    No Known Activations