© 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. 28717
    Prev
    Next
    INDEX
    Explanations

    terms related to hypoxia and its biological indicators

    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
    +0.24
    1.4%
    443
    +0.16
    1.0%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.24
    0.01
    182
    +0.16
    0.01
    302
    +0.12
    0.01
    Negative Logits
    >';
    -1.84
     happier
    -1.75
    zos
    -1.69
    ?'
    -1.62
    rfloor
    -1.62
    >'
    -1.56
    lew
    -1.54
    hood
    -1.51
    ?’
    -1.46
    cción
    -1.44
    POSITIVE LOGITS
    istor
    1.69
    uelle
    1.48
    erve
    1.43
     reaction
    1.40
     regimes
    1.38
    orphism
    1.32
     occasion
    1.31
    aline
    1.30
    iens
    1.30
     reactions
    1.29
    Activations Density 0.049%

    No Known Activations