© 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. 26104
    Prev
    Next
    INDEX
    Explanations

    function declarations in programming code

    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
    225
    +0.11
    0.7%
    95
    +0.10
    0.6%
    142
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.11
    0.02
    142
    +0.10
    0.02
    225
    +0.10
    0.02
    Negative Logits
    Ļª
    -4.04
    Ľ
    -3.92
    ħ
    -3.84
    ·¸
    -3.74
    Ĥ
    -3.72
    ¿½
    -3.71
    ľ
    -3.68
    ¸
    -3.67
    ´
    -3.66
    ĸ´
    -3.63
    POSITIVE LOGITS
    iones
    1.85
    #:
    1.76
    etto
    1.70
    ist
    1.67
    ificate
    1.66
    cia
    1.65
    nar
    1.62
    naire
    1.62
    nih
    1.62
    esan
    1.61
    Activations Density 0.057%

    No Known Activations