© 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. 26670
    Prev
    Next
    INDEX
    Explanations

    phrases expressing community care and support

    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
    +0.24
    1.4%
    464
    +0.15
    0.9%
    92
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.24
    0.18
    314
    +0.15
    0.19
    464
    +0.13
    0.11
    Negative Logits
    iquity
    -1.44
    :`
    -1.39
    oxin
    -1.37
    ôle
    -1.35
     replacing
    -1.34
    ellees
    -1.27
    "}](#
    -1.27
    ↵↵
    -1.27
    acity
    -1.26
    Argued
    -1.25
    POSITIVE LOGITS
    ĻĤ
    3.92
    IJ
    3.06
    Īĺ
    3.06
    ģ
    3.00
    ŀ
    2.96
    Ŀ
    2.93
    ı
    2.87
    ĸ
    2.84
    ¿
    2.83
    ¹
    2.80
    Activations Density 4.493%

    No Known Activations