© 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. 27766
    Prev
    Next
    INDEX
    Explanations

    instances of "DOM" related to Document Object Model coding references

    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
    458
    +0.13
    0.7%
    507
    +0.12
    0.7%
    189
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    507
    +0.13
    0.01
    189
    +0.12
    0.01
    190
    +0.11
    0.01
    Negative Logits
     chosen
    -1.71
    ureus
    -1.69
    ights
    -1.68
    ?'
    -1.60
    )](#
    -1.53
     usual
    -1.53
    rceil
    -1.50
    ?_
    -1.48
     mean
    -1.47
    aning
    -1.46
    POSITIVE LOGITS
    ª
    1.86
    AIN
    1.85
    ERTY
    1.68
    well
    1.63
    Script
    1.61
    caster
    1.61
    ioni
    1.60
    imab
    1.59
    strand
    1.58
    ®
    1.58
    Activations Density 0.125%

    No Known Activations