© 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. 25854
    Prev
    Next
    INDEX
    Explanations

    text that describes unclear or uncertain concepts

    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
    156
    +0.15
    0.8%
    376
    +0.15
    0.8%
    67
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.15
    0.01
    67
    +0.15
    0.01
    408
    +0.14
    0.01
    Negative Logits
    sembles
    -2.10
    že
    -1.49
    pires
    -1.46
     curious
    -1.40
    stant
    -1.40
    rient
    -1.38
    pired
    -1.32
     mismo
    -1.32
     accomplished
    -1.31
     elected
    -1.30
    POSITIVE LOGITS
    erville
    1.83
    chat
    1.62
     (\<
    1.61
     (\>
    1.61
    erad
    1.58
    \[[@
    1.53
    idone
    1.53
    cue
    1.50
    etz
    1.48
    neck
    1.43
    Activations Density 0.006%

    No Known Activations