© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 24219
    Prev
    Next
    INDEX
    Explanations

    frequent occurrences of the word "the" in various contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    441
    +0.13
    0.7%
    455
    +0.12
    0.7%
    288
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.13
    0.09
    92
    +0.12
    0.09
    440
    +0.11
    0.05
    Negative Logits
     distressed
    -1.37
    etica
    -1.30
     completed
    -1.30
    lace
    -1.29
    ulations
    -1.28
    omen
    -1.28
    amp
    -1.27
    acha
    -1.27
    ZO
    -1.25
    igm
    -1.25
    POSITIVE LOGITS
    3.66
    <|outofrange|>
    3.66
    ↵
    3.66
    č↵
    3.66
     ↵
    3.66
    ↵↵
    3.66
    3.66
    ↵↵
    3.66
    3.66
    3.66
    Activations Density 1.140%

    No Known Activations