© 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. 25802
    Prev
    Next
    INDEX
    Explanations

    brands and types of "gear" and accessories related to technology or entertainment

    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
    23
    +0.14
    0.8%
    333
    +0.12
    0.7%
    360
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.14
    0.05
    360
    +0.12
    0.00
    374
    +0.11
    0.00
    Negative Logits
     leagues
    -2.09
     defense
    -1.69
     league
    -1.68
     maker
    -1.48
     sisters
    -1.47
     engines
    -1.43
     vessels
    -1.43
     franchise
    -1.43
     franch
    -1.42
    prising
    -1.39
    POSITIVE LOGITS
    TRODUCTION
    1.84
     yours
    1.63
    ciparum
    1.57
    ASE
    1.55
    actic
    1.53
    angs
    1.47
    oblot
    1.47
    ==========
    1.46
    abel
    1.45
    OME
    1.45
    Activations Density 2.189%

    No Known Activations