© 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. 23629
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional states or feelings

    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
    408
    +0.13
    0.7%
    98
    +0.12
    0.7%
    424
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    361
    +0.13
    0.04
    13
    +0.12
    0.04
    424
    +0.12
    0.03
    Negative Logits
    ')
    -1.82
    ').
    -1.78
     nonetheless
    -1.76
    '):
    -1.73
    '?"
    -1.66
    '?
    -1.65
     still
    -1.64
    ________________
    -1.62
    '),
    -1.57
    ');
    -1.53
    POSITIVE LOGITS
    »¿
    2.16
    ¢
    1.75
    pocket
    1.71
    ½
    1.70
    Ń
    1.67
     libraries
    1.61
    ró
    1.59
    Ĭ
    1.58
    ł
    1.54
    ¬
    1.48
    Activations Density 0.410%

    No Known Activations