© 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. 29340
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "mix" and its variations, indicating discussions about combinations or mixtures

    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
    376
    +0.17
    1.0%
    62
    +0.13
    0.7%
    439
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.17
    0.03
    439
    +0.13
    0.02
    78
    +0.12
    0.02
    Negative Logits
    ¡
    -2.12
    ³
    -2.07
    »¿
    -2.05
    ·¸
    -2.01
    ĨĴ
    -1.99
    ĻĤ
    -1.93
    Ĥ
    -1.84
    Ł
    -1.82
    ¯
    -1.81
    IJ
    -1.79
    POSITIVE LOGITS
    hart
    2.08
    vin
    1.96
    achine
    1.82
    ouin
    1.82
    engers
    1.78
    reich
    1.76
    func
    1.75
    quist
    1.74
    ieux
    1.73
    cores
    1.73
    Activations Density 0.015%

    No Known Activations