© 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. 26929
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasoning, especially questions of justification and purpose

    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
    92
    +0.12
    0.7%
    76
    +0.11
    0.7%
    167
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.12
    0.03
    497
    +0.11
    -0.04
    357
    +0.11
    0.03
    Negative Logits
    į
    -1.73
    ³
    -1.59
    ¥
    -1.56
    ĨĴ
    -1.52
     miscon
    -1.50
    Ĩ
    -1.50
    ĵ
    -1.48
     error
    -1.47
     intention
    -1.47
     inequ
    -1.46
    POSITIVE LOGITS
    cco
    1.45
    nier
    1.42
    gas
    1.40
    plants
    1.38
    gart
    1.37
    abouts
    1.31
    grade
    1.31
     floors
    1.29
    azzo
    1.26
     rides
    1.24
    Activations Density 2.508%

    No Known Activations