© 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. 25946
    Prev
    Next
    INDEX
    Explanations

    references to airlines

    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%
    315
    +0.12
    0.7%
    339
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.21
    0.01
    228
    +0.12
    0.01
    71
    +0.11
    0.01
    Negative Logits
    ras
    -1.61
    aly
    -1.59
    olic
    -1.50
     nephew
    -1.45
     seas
    -1.41
     shore
    -1.38
    rium
    -1.37
     accl
    -1.36
     married
    -1.35
    oll
    -1.35
    POSITIVE LOGITS
    »¿
    4.29
    Ł
    3.37
    ¡
    3.34
    ¥
    3.30
    ®
    3.28
    Ļª
    3.26
    ĨĴ
    3.18
    ·¸
    3.14
    ¤
    3.10
    Ľ
    3.08
    Activations Density 0.020%

    No Known Activations