© 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. 26863
    Prev
    Next
    INDEX
    Explanations

    instances of descriptions or terms used to characterize something

    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
    382
    +0.13
    0.7%
    486
    +0.12
    0.7%
    387
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    14
    +0.13
    0.07
    25
    +0.12
    0.05
    387
    +0.11
    0.05
    Negative Logits
    naments
    -1.50
     dated
    -1.38
     referring
    -1.34
    Ŀ
    -1.32
     treating
    -1.31
     recommending
    -1.31
    pers
    -1.31
     accompanied
    -1.31
    acing
    -1.30
    ¾
    -1.29
    POSITIVE LOGITS
    ardo
    1.61
    annon
    1.58
    ressor
    1.56
    icago
    1.54
    _;
    1.53
    ahu
    1.52
    ascus
    1.50
    .',
    1.49
     outlet
    1.47
    chaft
    1.46
    Activations Density 0.665%

    No Known Activations