© 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. 28365
    Prev
    Next
    INDEX
    Explanations

    the word "distinct" or variations of it

    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
    348
    +0.14
    0.8%
    378
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    378
    +0.14
    0.01
    348
    +0.12
    0.01
    388
    +0.11
    0.01
    Negative Logits
    onia
    -1.84
    nez
    -1.74
     hers
    -1.73
    ?).
    -1.62
     myself
    -1.60
     mine
    -1.55
    ?)
    -1.55
    opause
    -1.44
     Spacewatch
    -1.44
     her
    -1.43
    POSITIVE LOGITS
    ellate
    1.71
    inct
    1.53
    media
    1.48
    ributor
    1.48
    âĢŁ
    1.46
    rito
    1.45
    ril
    1.43
    raction
    1.41
    church
    1.40
    ention
    1.39
    Activations Density 0.007%

    No Known Activations