© 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. 25215
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "also."

    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
    213
    +0.12
    0.6%
    182
    +0.11
    0.6%
    323
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    168
    +0.12
    0.04
    213
    +0.11
    0.04
    323
    +0.10
    0.03
    Negative Logits
    ·
    -1.79
    Ļª
    -1.77
    ¦
    -1.53
    res
    -1.52
    ]{}
    -1.47
    ders
    -1.46
    ´
    -1.44
    Ĺ
    -1.39
    applicable
    -1.38
     shock
    -1.37
    POSITIVE LOGITS
     contributor
    1.70
    uce
    1.69
    chle
    1.68
    enda
    1.66
    zona
    1.65
    ÅĽÄĩ
    1.56
    insky
    1.52
    agne
    1.48
    msgstr
    1.48
    agna
    1.48
    Activations Density 0.114%

    No Known Activations