© 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 EvalsExportsAPI 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. 28744
    Prev
    Next
    INDEX
    Explanations

    the presence of copyright statements or legal disclaimers in the text

    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
    369
    +0.15
    0.8%
    497
    +0.14
    0.8%
    354
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.15
    0.02
    354
    +0.14
    0.02
    103
    +0.13
    0.02
    Negative Logits
     States
    -1.46
     streak
    -1.42
    noreply
    -1.40
    matically
    -1.39
     Crick
    -1.37
    avirus
    -1.36
    romy
    -1.34
    ments
    -1.34
    ially
    -1.34
    lain
    -1.33
    POSITIVE LOGITS
    ®
    1.91
    ģ
    1.84
    º
    1.77
    veau
    1.74
    ª
    1.72
    «
    1.69
    ©
    1.69
    ĺ
    1.67
    IER
    1.65
    Ń
    1.61
    Activations Density 1.020%

    No Known Activations