© 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. 0-MLP-SM
    11. 26621
    Prev
    Next
    INDEX
    Explanations

    instances of expressions of disbelief or incredulity

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    80
    +0.16
    0.9%
    154
    +0.13
    0.7%
    119
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.16
    0.40
    53
    +0.13
    0.42
    56
    +0.12
    0.11
    Negative Logits
    mary
    -1.69
    arious
    -1.68
    ycin
    -1.62
    umab
    -1.58
    wright
    -1.58
     alone
    -1.57
    taire
    -1.45
    ubicin
    -1.45
    atics
    -1.43
    usa
    -1.43
    POSITIVE LOGITS
    µ
    3.78
    ®
    3.67
    ī
    3.66
    ²
    3.52
    ·¸
    3.48
    ¬
    3.36
    ½
    3.33
    Ļª
    3.32
    »¿
    3.18
    »
    3.18
    Activations Density 4.681%

    No Known Activations