© 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. 30057
    Prev
    Next
    INDEX
    Explanations

    strong statements regarding controversial social issues

    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
    478
    +0.23
    1.3%
    377
    +0.12
    0.6%
    115
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.23
    0.05
    437
    +0.12
    0.04
    187
    +0.11
    0.05
    Negative Logits
     ÂĹ
    -1.74
    ulose
    -1.60
    ellar
    -1.53
    irubin
    -1.53
    ginx
    -1.50
    ies
    -1.45
    assic
    -1.44
    izz
    -1.42
    yrus
    -1.42
    nikov
    -1.41
    POSITIVE LOGITS
    ¸
    1.92
    Ĭ
    1.67
    ÑĢав
    1.62
    Ķ
    1.58
    ¥
    1.47
    ¼
    1.45
    unnumbered
    1.44
    Ĵ
    1.36
    Ļ
    1.35
    _>
    1.34
    Activations Density 0.057%

    No Known Activations