© 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. 28870
    Prev
    Next
    INDEX
    Explanations

    references to forests

    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
    +0.12
    0.7%
    100
    +0.11
    0.6%
    451
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.12
    0.01
    180
    +0.11
    0.01
    312
    +0.11
    0.01
    Negative Logits
    Ń
    -2.06
    ĥ½
    -2.04
    ĸ´
    -1.98
    ľĵ
    -1.88
    ĨĴ
    -1.84
    Ŀ
    -1.77
     '</
    -1.69
     valuable
    -1.66
    ¬
    -1.62
    ĺ
    -1.61
    POSITIVE LOGITS
    bank
    1.79
    worker
    1.71
    bourne
    1.67
    workers
    1.63
    aceut
    1.55
    ÃŃa
    1.55
    dale
    1.54
    yard
    1.54
    notes
    1.53
    ems
    1.52
    Activations Density 0.007%

    No Known Activations