© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26801
    Prev
    Next
    INDEX
    Explanations

    symbols or characters that serve as placeholders or separators

    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
    +0.19
    1.0%
    431
    +0.12
    0.7%
    332
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.19
    0.06
    332
    +0.12
    0.05
    458
    +0.12
    0.04
    Negative Logits
    blogger
    -1.72
    disambiguation
    -1.54
    orect
    -1.51
     /*!
    -1.44
    ÅĪ
    -1.41
    ===============
    -1.40
    rolet
    -1.39
    =============
    -1.38
     synonymous
    -1.38
    CTYPE
    -1.35
    POSITIVE LOGITS
    mates
    1.79
    mate
    1.55
    selves
    1.45
     conclusions
    1.38
     Hig
    1.37
     Improvement
    1.35
     agents
    1.34
     officers
    1.34
     Stevens
    1.29
     Stories
    1.28
    Activations Density 0.287%

    No Known Activations