© 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. 0-MLP-SM
    11. 28331
    Prev
    Next
    INDEX
    Explanations

    sentence-ending periods

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    88
    +0.13
    0.7%
    58
    +0.12
    0.6%
    99
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.13
    0.55
    56
    +0.12
    0.18
    203
    +0.11
    0.38
    Negative Logits
     crafts
    -1.46
     wisely
    -1.41
     society
    -1.40
    eration
    -1.35
    cano
    -1.33
     births
    -1.32
     talents
    -1.32
     awarded
    -1.32
     resources
    -1.31
     culture
    -1.29
    POSITIVE LOGITS
    »¿
    3.49
    ĨĴ
    3.30
    ¼
    3.10
    Ļª
    2.97
    ·¸
    2.93
    ¢
    2.78
    «
    2.70
    ¿
    2.65
    ³
    2.59
    ĩ
    2.59
    Activations Density 3.565%

    No Known Activations