© 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. 22863
    Prev
    Next
    INDEX
    Explanations

    references to polling data and survey results related to political themes or candidates

    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
    156
    +0.16
    0.9%
    432
    +0.13
    0.7%
    46
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.16
    0.05
    23
    +0.13
    0.03
    232
    +0.12
    0.05
    Negative Logits
     ahead
    -1.51
    Ī
    -1.43
     classmates
    -1.40
     drawings
    -1.38
    '."
    -1.37
    \]](
    -1.36
    aded
    -1.36
     somewhere
    -1.35
    odor
    -1.33
    ]>
    -1.33
    POSITIVE LOGITS
     des
    1.49
    jar
    1.41
     bunch
    1.40
    ious
    1.35
     Exec
    1.31
    upt
    1.31
    ossa
    1.29
    rar
    1.28
    exe
    1.28
    verse
    1.27
    Activations Density 0.782%

    No Known Activations