© 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. 28657
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions related to anemia

    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
    149
    +0.14
    0.8%
    376
    +0.14
    0.8%
    2
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.14
    0.01
    410
    +0.14
    0.01
    324
    +0.12
    0.01
    Negative Logits
    tat
    -1.58
    nership
    -1.55
    ikh
    -1.48
    purpose
    -1.45
    odge
    -1.43
    tons
    -1.43
     agents
    -1.43
    orems
    -1.42
    ANCE
    -1.42
    CHANTABILITY
    -1.41
    POSITIVE LOGITS
    ±
    1.64
    ilities
    1.60
    erobic
    1.57
    idity
    1.51
    strom
    1.51
    ulator
    1.50
    uncher
    1.45
    ilee
    1.43
    halt
    1.42
    ilty
    1.41
    Activations Density 0.008%

    No Known Activations