© 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. 23202
    Prev
    Next
    INDEX
    Explanations

    occurrences and references to robots or robotic technology

    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
    458
    +0.13
    0.7%
    336
    +0.13
    0.7%
    511
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.13
    0.03
    412
    +0.13
    0.05
    458
    +0.12
    0.03
    Negative Logits
     features
    -1.57
     rendition
    -1.56
     acts
    -1.50
     representation
    -1.48
    ",
    -1.46
     appearance
    -1.39
     capt
    -1.39
     posts
    -1.38
     molecular
    -1.38
     nor
    -1.37
    POSITIVE LOGITS
    zech
    1.43
    big
    1.41
    ipro
    1.39
    ither
    1.38
    áĥĺ
    1.38
    igs
    1.34
    main
    1.33
    IPE
    1.32
    awa
    1.32
    IOR
    1.31
    Activations Density 0.965%

    No Known Activations