© 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. 23937
    Prev
    Next
    INDEX
    Explanations

    medical terminology and references to health conditions and treatments

    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
    74
    +0.12
    0.6%
    273
    +0.11
    0.6%
    339
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.12
    0.07
    275
    +0.11
    0.01
    86
    +0.10
    0.06
    Negative Logits
     louder
    -1.36
    cit
    -1.33
    others
    -1.32
     spoken
    -1.31
    hered
    -1.30
    SEE
    -1.27
     scream
    -1.26
    uttered
    -1.25
    "'
    -1.24
     crying
    -1.24
    POSITIVE LOGITS
    ¤
    3.51
    ¬
    3.37
    ī
    3.32
    ¯
    3.23
    ·
    3.19
    ¦
    3.18
    µ
    3.18
    ĸ
    3.15
    ¨
    3.13
    Ł
    3.12
    Activations Density 1.122%

    No Known Activations