© 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. 26593
    Prev
    Next
    INDEX
    Explanations

    code snippets or function definitions

    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
    478
    +0.11
    0.6%
    177
    +0.11
    0.6%
    245
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.11
    0.01
    245
    +0.11
    0.02
    175
    +0.11
    0.02
    Negative Logits
    »¿
    -3.02
    Ĥ¬
    -2.14
    ¬
    -2.09
    ·¸
    -2.06
    ±
    -2.04
    ´
    -1.95
    ¨
    -1.95
    ŀ
    -1.93
    ¢
    -1.91
    Ĺ
    -1.91
    POSITIVE LOGITS
    unnumbered
    1.69
    typeof
    1.62
    urate
    1.42
    ************************
    1.40
    orge
    1.37
    quo
    1.35
    mina
    1.35
     involving
    1.34
     sigh
    1.34
     messaging
    1.32
    Activations Density 0.035%

    No Known Activations