© 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. 24807
    Prev
    Next
    INDEX
    Explanations

    references to size and scale

    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
    177
    +0.12
    0.7%
    501
    +0.12
    0.7%
    38
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.12
    0.04
    177
    +0.12
    0.03
    501
    +0.12
    0.04
    Negative Logits
    ĥ½
    -2.14
    ĻĤ
    -2.00
    »¿
    -1.91
    ¬
    -1.90
    ¡
    -1.88
    ĸ´
    -1.88
    Ĺ
    -1.86
    ·¸
    -1.83
    į
    -1.77
    º
    -1.74
    POSITIVE LOGITS
    ively
    1.57
    ivist
    1.56
    ief
    1.54
     controversy
    1.46
    strom
    1.45
    ivism
    1.42
    iast
    1.40
     refers
    1.39
    roller
    1.39
    itis
    1.38
    Activations Density 0.342%

    No Known Activations