© 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. 0-MLP-SM
    11. 29254
    Prev
    Next
    INDEX
    Explanations

    lists of important personal and legal documents

    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
    449
    +0.13
    0.7%
    294
    +0.12
    0.7%
    213
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.40
    53
    +0.12
    0.42
    56
    +0.11
    0.11
    Negative Logits
    ľ
    -2.05
    į
    -1.93
    ļ
    -1.81
    Ķ
    -1.79
    ¸
    -1.73
    ľĵ
    -1.71
    isters
    -1.68
    -1.65
    -1.65
    -1.65
    POSITIVE LOGITS
    od
    1.58
    ”?
    1.57
    odi
    1.55
     milk
    1.54
    illed
    1.51
    pled
    1.49
    ñ
    1.47
    oth
    1.47
     thirst
    1.43
    ods
    1.42
    Activations Density 4.665%

    No Known Activations