© 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. 26605
    Prev
    Next
    INDEX
    Explanations

    the presence of technical terms relevant to data structures and their relationships in programming contexts

    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
    156
    +0.38
    2.3%
    464
    +0.15
    0.9%
    484
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.38
    0.52
    71
    +0.15
    0.52
    288
    +0.13
    0.48
    Negative Logits
    ção
    -1.52
    oxin
    -1.40
    ôle
    -1.39
    iquity
    -1.38
    Argued
    -1.36
     replacing
    -1.30
    idence
    -1.30
     ]{}
    -1.27
    iding
    -1.26
    osition
    -1.25
    POSITIVE LOGITS
    ĻĤ
    3.26
    Īĺ
    2.64
    ģ
    2.64
    ŀ
    2.46
    Ļ
    2.44
    IJ
    2.39
    Ļª
    2.33
    ĸ
    2.33
    ĺ
    2.29
    ¿
    2.29
    Activations Density 6.375%

    No Known Activations