© 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. 29237
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thrown" and its variations

    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
    376
    +0.16
    0.9%
    162
    +0.14
    0.8%
    148
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.16
    0.02
    127
    +0.14
    0.02
    444
    +0.13
    0.02
    Negative Logits
    »¿
    -2.49
    ī
    -2.38
    Ī
    -2.17
    Ĩ
    -2.09
    «
    -2.07
    Ń
    -2.01
    ĵ
    -2.00
    ĥ½
    -2.00
    ª
    -1.95
    ¿
    -1.94
    POSITIVE LOGITS
    aways
    1.89
    away
    1.83
    pick
    1.67
    liner
    1.66
    lasses
    1.59
    inger
    1.56
    guns
    1.56
    lass
    1.49
    note
    1.49
    tails
    1.49
    Activations Density 0.023%

    No Known Activations