© 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. 2-MLP-SM
    11. 24098
    Prev
    Next
    INDEX
    Explanations

    mentions of villages and associated contexts

    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
    23
    +0.13
    0.7%
    120
    +0.11
    0.6%
    73
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.13
    0.02
    120
    +0.11
    0.02
    198
    +0.11
    0.02
    Negative Logits
    ĻĤ
    -2.61
    ¹
    -2.17
    £
    -2.06
    Ĵ
    -2.01
    ŀ
    -2.00
    ĵ
    -1.99
    ļ
    -1.93
    ¾
    -1.88
    ĭ
    -1.86
    ½
    -1.84
    POSITIVE LOGITS
    )|$(
    1.61
     withstand
    1.60
    otransferase
    1.58
    acity
    1.57
    fulness
    1.56
    ,''
    1.50
    atal
    1.46
    |$.
    1.43
    emic
    1.42
    iox
    1.41
    Activations Density 0.147%

    No Known Activations