© 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. 26706
    Prev
    Next
    INDEX
    Explanations

    instances of the letter "e"

    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
    +0.19
    1.0%
    398
    +0.13
    0.7%
    50
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.19
    0.03
    332
    +0.13
    0.04
    50
    +0.12
    0.02
    Negative Logits
    iments
    -1.42
    iment
    -1.40
    meter
    -1.39
     worden
    -1.39
    emy
    -1.39
     extends
    -1.35
    igent
    -1.35
     chambers
    -1.35
    atar
    -1.35
    dimensional
    -1.33
    POSITIVE LOGITS
    ĻĤ
    2.33
    ĩ
    1.95
    Ħ
    1.70
    ¬
    1.69
    ¼
    1.67
    ¿
    1.62
    ¿½
    1.59
     HN
    1.55
    ®
    1.53
     DISCLAIM
    1.51
    Activations Density 0.370%

    No Known Activations