© 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. 28346
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, particularly in the northeast region

    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
    +0.21
    1.2%
    107
    +0.13
    0.8%
    362
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.21
    0.01
    459
    +0.13
    0.01
    119
    +0.13
    0.01
    Negative Logits
    athered
    -1.75
    aves
    -1.74
    ching
    -1.67
    aved
    -1.65
    arner
    -1.62
    akin
    -1.62
    eter
    -1.61
    ostat
    -1.58
    urer
    -1.56
    edom
    -1.54
    POSITIVE LOGITS
    Ł
    3.84
    ¸
    3.71
    µ
    3.60
    ·¸
    3.58
    ²
    3.56
    ĸ
    3.55
    ¹
    3.54
    ł
    3.52
    ļ
    3.44
    »
    3.43
    Activations Density 0.002%

    No Known Activations