© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27707
    Prev
    Next
    INDEX
    Explanations

    instances of the word "commerce."

    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
    460
    +0.11
    0.7%
    392
    +0.11
    0.7%
    119
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.11
    0.01
    119
    +0.11
    0.01
    19
    +0.11
    0.01
    Negative Logits
     bowed
    -1.67
    ij
    -1.58
    IJ
    -1.53
     crossed
    -1.45
     NULL
    -1.44
    ³
    -1.43
     selected
    -1.41
     Gay
    -1.41
     whole
    -1.40
     gay
    -1.37
    POSITIVE LOGITS
    vist
    2.15
    istry
    2.04
    naire
    1.99
    eer
    1.92
    esan
    1.91
    yer
    1.90
    fors
    1.90
    processor
    1.85
    ilage
    1.82
    bard
    1.77
    Activations Density 0.313%

    No Known Activations