© 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. 24202
    Prev
    Next
    INDEX
    Explanations

    the various medical syndromes and disorders

    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
    478
    +0.17
    1.0%
    217
    +0.13
    0.8%
    236
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.17
    0.02
    236
    +0.13
    0.01
    217
    +0.12
    0.01
    Negative Logits
    Ĺ
    -3.49
    ¡
    -3.38
    İ
    -3.31
    Ļ
    -3.30
    £
    -3.27
    Ľ
    -3.25
    ľ
    -3.14
    ļ
    -3.13
    ij
    -3.09
    ¤
    -3.09
    POSITIVE LOGITS
    iary
    1.62
     pray
    1.50
     NOTICE
    1.49
     parte
    1.49
    :`
    1.49
     zip
    1.41
     FUN
    1.41
    emy
    1.41
     orderly
    1.41
     bod
    1.41
    Activations Density 0.062%

    No Known Activations