© 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 EvalsExportsinterp-engineNEWAPI 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. 30510
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or sentence boundaries

    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
    106
    +0.19
    1.1%
    346
    +0.15
    0.9%
    417
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.19
    0.36
    23
    +0.15
    0.31
    494
    +0.13
    0.25
    Negative Logits
    ricular
    -1.66
     mutagenesis
    -1.64
    "}](#
    -1.60
    ozo
    -1.59
    oning
    -1.59
    ople
    -1.54
    zymes
    -1.52
     mutations
    -1.48
     urging
    -1.42
    bons
    -1.42
    POSITIVE LOGITS
    ³
    2.89
    Īĺ
    2.87
    Ļª
    2.84
    ·¸
    2.84
    Ĺ
    2.83
    ĻĤ
    2.83
    ¿½
    2.83
    ĥ½
    2.80
    ↵
    2.73
    ↵
    2.73
    Activations Density 3.072%

    No Known Activations