© 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. 24321
    Prev
    Next
    INDEX
    Explanations

    terms related to acute medical conditions or situations

    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
    156
    +0.17
    1.0%
    38
    +0.13
    0.7%
    373
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.17
    0.00
    374
    +0.13
    0.00
    122
    +0.13
    0.01
    Negative Logits
    ĻĤ
    -3.47
    ĥ½
    -3.35
    »¿
    -2.87
    ¸
    -2.70
    ĩ
    -2.70
    °
    -2.58
    ľ
    -2.57
    £
    -2.52
    ij
    -2.39
    ĭ
    -2.25
    POSITIVE LOGITS
     Vote
    1.67
    ride
    1.59
     Evil
    1.57
     baking
    1.57
     Holiday
    1.55
    ially
    1.51
    stown
    1.50
     supreme
    1.49
     Citizens
    1.46
     LOVE
    1.46
    Activations Density 0.042%

    No Known Activations