© 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. 24692
    Prev
    Next
    INDEX
    Explanations

    sentences that provide cooking instructions and steps for preparing food

    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
    130
    +0.11
    0.7%
    103
    +0.11
    0.6%
    327
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.11
    0.13
    189
    +0.11
    0.10
    409
    +0.10
    0.10
    Negative Logits
    IJ
    -2.45
    ³
    -2.42
    ¿½
    -2.37
    ĻĤ
    -2.36
    ¦
    -2.32
    ´
    -2.21
    ·
    -2.17
    »¿
    -2.16
    Ħ
    -2.14
    Ĺ
    -2.07
    POSITIVE LOGITS
    insky
    1.93
    udad
    1.87
    pora
    1.86
    buntu
    1.80
    enix
    1.80
    official
    1.78
    vist
    1.75
    ÃŃf
    1.73
    doc
    1.71
    ű
    1.69
    Activations Density 1.310%

    No Known Activations