© 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. 30422
    Prev
    Next
    INDEX
    Explanations

    repeated conjunctions within connected phrases or clauses

    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
    261
    +0.13
    0.7%
    324
    +0.12
    0.7%
    414
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.13
    0.45
    209
    +0.12
    0.29
    402
    +0.12
    0.26
    Negative Logits
     particular
    -1.71
     probing
    -1.57
     than
    -1.55
     successful
    -1.53
     %
    -1.50
    nis
    -1.45
    ure
    -1.44
    ures
    -1.39
     ?>
    -1.39
     transmission
    -1.36
    POSITIVE LOGITS
    ¹
    2.40
    »¿
    2.36
    IJ
    2.22
    ľĵ
    2.21
    ¢
    2.17
    ³
    2.14
    ¨
    2.12
    ·¸
    2.11
    ¶
    2.06
    »
    2.06
    Activations Density 1.557%

    No Known Activations