© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25363
    Prev
    Next
    INDEX
    Explanations

    instances of specific programming or scripting code and syntax

    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
    176
    +0.15
    0.8%
    23
    +0.13
    0.7%
    292
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.15
    0.51
    473
    +0.13
    0.50
    49
    +0.12
    0.50
    Negative Logits
    ullah
    -1.76
     Fed
    -1.59
    rico
    -1.54
     regimes
    -1.53
    Verlag
    -1.52
    umbered
    -1.51
     economist
    -1.48
    wick
    -1.43
    ktop
    -1.42
     Ludwig
    -1.39
    POSITIVE LOGITS
    shoot
    1.69
    rays
    1.51
    ))$
    1.48
     bye
    1.40
    sing
    1.38
     results
    1.37
    spir
    1.37
    "))
    1.36
    ETHOD
    1.32
     Rs
    1.31
    Activations Density 4.540%

    No Known Activations