© 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. 25360
    Prev
    Next
    INDEX
    Explanations

    references to roles or positions related to operational or functional work

    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
    362
    +0.14
    0.8%
    266
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.14
    0.01
    16
    +0.12
    0.01
    294
    +0.11
    0.01
    Negative Logits
     happier
    -1.63
    oxacin
    -1.45
    than
    -1.41
    >();
    -1.40
    ĥ½
    -1.38
    ž
    -1.37
     Hope
    -1.36
     dignity
    -1.33
    ethyl
    -1.31
    ķ
    -1.30
    POSITIVE LOGITS
    ISPR
    1.95
    issance
    1.65
    "}](#
    1.65
    idades
    1.63
    merce
    1.60
    facts
    1.58
    enium
    1.57
    uary
    1.57
     senses
    1.56
    imetry
    1.52
    Activations Density 0.009%

    No Known Activations