© 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. 0-MLP-SM
    11. 28414
    Prev
    Next
    INDEX
    Explanations

    the word "cal" in various contexts, particularly in relation to calories

    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
    177
    +0.12
    0.7%
    475
    +0.12
    0.7%
    274
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.12
    0.02
    402
    +0.12
    0.02
    28
    +0.11
    0.02
    Negative Logits
    ·¸
    -2.16
    Ĥ¬
    -2.11
    ĨĴ
    -2.07
    ĥ
    -1.86
    ³
    -1.75
    ¾
    -1.64
    Ļª
    -1.51
    ¿
    -1.50
    -1.50
    »¿
    -1.50
    POSITIVE LOGITS
    ifornia
    1.70
    oupe
    1.65
    endar
    1.60
    culated
    1.60
    gary
    1.57
    prote
    1.49
    lee
    1.46
    ientes
    1.42
    ais
    1.41
    fonts
    1.41
    Activations Density 0.544%

    No Known Activations