© 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 EvalsExportsAPI 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. 29062
    Prev
    Next
    INDEX
    Explanations

    references to engineers and engineering roles

    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
    +0.32
    2.0%
    376
    +0.18
    1.1%
    365
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    323
    +0.32
    0.01
    156
    +0.18
    0.01
    365
    +0.11
    0.01
    Negative Logits
     transgender
    -1.55
    opy
    -1.52
    ĥ½
    -1.50
    hed
    -1.49
    inberg
    -1.46
     highest
    -1.45
     Supreme
    -1.40
     â
    -1.31
     Legislature
    -1.30
     LGBT
    -1.29
    POSITIVE LOGITS
    liness
    1.90
    ships
    1.76
    pieces
    1.60
    zilla
    1.57
    ship
    1.53
    iments
    1.53
    asks
    1.50
    ajas
    1.50
     defeats
    1.50
    ically
    1.46
    Activations Density 0.017%

    No Known Activations