© 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. 25648
    Prev
    Next
    INDEX
    Explanations

    phrases related to prohibitions or limitations

    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
    +0.19
    1.0%
    415
    +0.11
    0.6%
    457
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    415
    +0.19
    0.01
    3
    +0.11
    0.01
    433
    +0.11
    0.01
    Negative Logits
    »
    -1.93
    ·¸
    -1.93
    ľ
    -1.89
    §
    -1.88
    Ķ
    -1.86
    İ
    -1.79
    ´
    -1.77
    º
    -1.74
    Ľ
    -1.73
    ģ
    -1.72
    POSITIVE LOGITS
    ielle
    1.80
    ourse
    1.56
    isi
    1.56
    avel
    1.51
    lane
    1.51
     park
    1.49
    ière
    1.48
    pile
    1.45
     accession
    1.41
    asse
    1.41
    Activations Density 0.017%

    No Known Activations