© 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. 25938
    Prev
    Next
    INDEX
    Explanations

    references to specific types of snapshots or monitoring data

    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
    +0.14
    0.8%
    370
    +0.11
    0.6%
    466
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.04
    370
    +0.11
    0.03
    249
    +0.11
    0.02
    Negative Logits
    ¼
    -3.05
    Ľ
    -2.85
    ĻĤ
    -2.65
    ĺ
    -2.64
    ¨
    -2.60
    Īĺ
    -2.60
    Į
    -2.59
    ´
    -2.59
    ©
    -2.56
    ģ
    -2.55
    POSITIVE LOGITS
    ://
    1.83
    nement
    1.65
    illance
    1.64
    emente
    1.48
    ÃŃvel
    1.47
    mentation
    1.47
    ment
    1.47
    eer
    1.46
    aurus
    1.46
    ÄĽ
    1.44
    Activations Density 0.183%

    No Known Activations