© 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 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. 24841
    Prev
    Next
    INDEX
    Explanations

    references to traditional or standard methods and protocols

    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
    96
    +0.14
    0.8%
    170
    +0.12
    0.6%
    82
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.14
    0.01
    440
    +0.12
    0.01
    485
    +0.11
    0.01
    Negative Logits
    ils
    -1.66
     imports
    -1.58
     abroad
    -1.44
     rely
    -1.39
    pp
    -1.33
     demonstrate
    -1.32
    ]{}\
    -1.32
     nations
    -1.29
     progeny
    -1.29
     distinguished
    -1.28
    POSITIVE LOGITS
    ¿
    2.48
    Īĺ
    2.42
    »
    2.39
    ĨĴ
    2.34
    ĻĤ
    2.31
    Ķ
    2.28
    2.27
     ↵
    2.27
    2.27
    ↵
    2.27
    Activations Density 0.113%

    No Known Activations