© 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. 28244
    Prev
    Next
    INDEX
    Explanations

    mentions of significant quantities or numbers in the text

    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
    391
    +0.12
    0.7%
    362
    +0.12
    0.6%
    122
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    416
    +0.12
    0.01
    122
    +0.12
    0.01
    391
    +0.11
    0.01
    Negative Logits
    tering
    -1.77
    ICAN
    -1.75
    tered
    -1.71
    dule
    -1.70
    IC
    -1.67
    chers
    -1.64
    icar
    -1.62
    des
    -1.56
    ICA
    -1.54
    rians
    -1.53
    POSITIVE LOGITS
    Ļª
    2.39
    ª
    2.31
    ¸
    2.21
    Į
    2.04
    Ķ
    1.98
    ķ
    1.96
    ŀ
    1.92
    ħ
    1.91
    Ĵ
    1.84
    Ĭ
    1.84
    Activations Density 0.011%

    No Known Activations