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

    Neuronpedia

    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. 26899
    Prev
    Next
    INDEX
    Explanations

    molecular and genetic terms related to cellular structure

    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
    156
    +0.17
    1.0%
    376
    +0.11
    0.7%
    292
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.17
    0.01
    330
    +0.11
    0.01
    105
    +0.10
    0.01
    Negative Logits
     your
    -1.83
     their
    -1.79
    ĥ½
    -1.75
     thee
    -1.64
     each
    -1.62
     someone
    -1.61
     you
    -1.59
     yours
    -1.53
    §
    -1.52
    LLOW
    -1.50
    POSITIVE LOGITS
    bourne
    2.08
    iom
    1.68
    "}](#
    1.67
    pool
    1.67
    bank
    1.63
    iop
    1.60
    feet
    1.60
    opoulos
    1.51
    ional
    1.50
    isl
    1.49
    Activations Density 0.009%

    No Known Activations