© 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. 2-MLP-SM
    11. 24341
    Prev
    Next
    INDEX
    Explanations

    terms related to medical diagnoses and the process of diagnosing medical conditions

    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
    392
    +0.15
    0.8%
    160
    +0.13
    0.7%
    319
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.15
    0.01
    78
    +0.13
    0.01
    392
    +0.12
    0.02
    Negative Logits
    £
    -4.71
    ±
    -4.34
    ı
    -4.11
    Ĺ
    -4.09
    Ľ
    -4.09
    ľĵ
    -4.07
    ħ
    -4.04
    ³
    -4.00
    Ļ
    -3.92
    ¤
    -3.90
    POSITIVE LOGITS
     input
    1.58
     yourselves
    1.56
     synthe
    1.50
     Output
    1.47
     output
    1.43
     Invention
    1.42
     feasible
    1.40
     inputs
    1.38
     sufficiently
    1.37
     startup
    1.36
    Activations Density 0.157%

    No Known Activations