© 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. 0-MLP-SM
    11. 29901
    Prev
    Next
    INDEX
    Explanations

    instances of the word "need."

    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
    364
    +0.12
    0.6%
    234
    +0.11
    0.6%
    159
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.12
    0.07
    14
    +0.11
    0.07
    197
    +0.11
    0.07
    Negative Logits
    versions
    -1.42
    cluding
    -1.39
    version
    -1.37
     yet
    -1.31
    ĩ
    -1.30
    ictions
    -1.30
    kim
    -1.29
     thumbs
    -1.27
    autre
    -1.27
     Stafford
    -1.27
    POSITIVE LOGITS
     myself
    1.60
    aintiff
    1.59
     Court
    1.56
    mma
    1.54
     (\[
    1.46
    beck
    1.44
    quez
    1.43
    heed
    1.41
    ===
    1.36
     github
    1.36
    Activations Density 0.217%

    No Known Activations