© 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. 26653
    Prev
    Next
    INDEX
    Explanations

    references to atherosclerosis or related medical terminology

    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
    +0.33
    2.1%
    103
    +0.11
    0.7%
    71
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.33
    0.01
    103
    +0.11
    0.01
    184
    +0.11
    0.01
    Negative Logits
    »
    -2.04
    ĥ½
    -1.90
    ¿½
    -1.80
    ı
    -1.72
    į
    -1.65
    ¯
    -1.61
    Ķ
    -1.59
    obbsee
    -1.55
    ½
    -1.52
    Ń
    -1.51
    POSITIVE LOGITS
    break
    1.66
     amounts
    1.64
     HV
    1.44
     lumin
    1.44
    ually
    1.42
    burg
    1.42
     defense
    1.41
     course
    1.38
    sev
    1.32
     cause
    1.32
    Activations Density 0.008%

    No Known Activations