© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24651
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to clarity, consistency, and the presence of uncertainty in contexts

    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
    421
    +0.12
    0.7%
    131
    +0.12
    0.7%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.12
    0.05
    122
    +0.12
    0.04
    104
    +0.11
    0.04
    Negative Logits
    Īĺ
    -2.67
    ĥ
    -2.66
    Ģ
    -2.53
    ĺ
    -2.46
    ģ
    -2.41
    ĥ½
    -2.34
    IJ
    -2.29
    ↵↵
    -2.28
    ↵
    -2.28
    <|outofrange|>
    -2.28
    POSITIVE LOGITS
    ories
    1.53
    levels
    1.51
    orie
    1.50
    hood
    1.49
    ity
    1.48
     Board
    1.45
    bie
    1.44
     Wizard
    1.42
    ums
    1.41
    ori
    1.39
    Activations Density 0.592%

    No Known Activations