© 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. 26030
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "press" and its variations, suggesting a focus on publishing or related activities

    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
    341
    +0.13
    0.8%
    217
    +0.13
    0.7%
    300
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.13
    0.02
    300
    +0.13
    0.01
    336
    +0.10
    0.01
    Negative Logits
    ¿½
    -1.98
    ı
    -1.89
     yours
    -1.88
     cross
    -1.86
     hers
    -1.78
     everything
    -1.74
     theirs
    -1.71
    ´
    -1.66
     else
    -1.66
    ķ
    -1.65
    POSITIVE LOGITS
    ive
    1.94
    ional
    1.86
    iveness
    1.85
    rant
    1.83
    assic
    1.80
    esan
    1.79
    edly
    1.77
    urized
    1.75
    bars
    1.71
    ioni
    1.68
    Activations Density 0.016%

    No Known Activations