© 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. 26831
    Prev
    Next
    INDEX
    Explanations

    components related to scientific and technical summarization

    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
    +0.15
    0.8%
    218
    +0.11
    0.6%
    211
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.15
    0.01
    218
    +0.11
    0.06
    23
    +0.10
    0.03
    Negative Logits
    seys
    -1.56
    ène
    -1.45
     goals
    -1.43
     HN
    -1.40
    ivism
    -1.38
     Saturn
    -1.36
    ivist
    -1.36
     favorites
    -1.35
    ĨĴ
    -1.34
    ÃŃas
    -1.34
    POSITIVE LOGITS
    rror
    1.58
    wl
    1.46
    grant
    1.43
    quired
    1.42
    bral
    1.40
    acillus
    1.40
    nexpected
    1.39
     classified
    1.34
    atal
    1.34
    ittal
    1.33
    Activations Density 1.169%

    No Known Activations