© 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. 25324
    Prev
    Next
    INDEX
    Explanations

    medical symptoms and related clinical findings

    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
    169
    +0.15
    0.8%
    127
    +0.11
    0.6%
    23
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    169
    +0.15
    0.03
    168
    +0.11
    0.02
    293
    +0.10
    0.02
    Negative Logits
    Ĺ
    -2.23
    Ĩ
    -2.18
    ĻĤ
    -2.15
    ¦
    -2.13
    £
    -2.10
    Ļ
    -2.09
    ¨
    -2.09
    ľĵ
    -2.06
    ¡
    -2.05
    ħ
    -2.01
    POSITIVE LOGITS
    "|
    1.65
    iline
    1.55
    derer
    1.50
    liness
    1.43
    emaker
    1.42
     enough
    1.39
    "_
    1.39
    ders
    1.37
     properly
    1.36
     dividends
    1.35
    Activations Density 0.173%

    No Known Activations