© 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. 23031
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional distress and concern

    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
    329
    +0.13
    0.7%
    458
    +0.10
    0.6%
    92
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.13
    0.10
    454
    +0.10
    0.03
    502
    +0.10
    0.14
    Negative Logits
     plaintiff
    -1.93
    ities
    -1.71
     coats
    -1.58
     plaintiffs
    -1.56
     loosely
    -1.53
    acity
    -1.50
    hift
    -1.49
     rapidly
    -1.48
     Plaintiff
    -1.47
     defendant
    -1.47
    POSITIVE LOGITS
    £
    2.04
    ģ
    2.00
    ĻĤ
    1.85
    ene
    1.79
    ĺ
    1.73
     0000000000000000000000000000000000
    1.60
    »¿
    1.60
    Ļ
    1.57
    ĥ½
    1.56
    ĸ
    1.54
    Activations Density 3.170%

    No Known Activations