© 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 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. 28650
    Prev
    Next
    INDEX
    Explanations

    references to mathematical equations in the text

    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
    +0.14
    0.8%
    10
    +0.13
    0.7%
    381
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.14
    0.01
    481
    +0.13
    0.01
    10
    +0.12
    0.01
    Negative Logits
    ¯
    -1.89
    ¿
    -1.72
    ĥ½
    -1.65
    reland
    -1.52
    ename
    -1.48
     inventors
    -1.47
    arrant
    -1.44
     apologize
    -1.42
    ½
    -1.40
    ove
    -1.38
    POSITIVE LOGITS
    naire
    1.76
    locked
    1.76
    ic
    1.71
    {"
    1.56
     puzzles
    1.47
    "}](#
    1.47
    less
    1.46
    flow
    1.44
    making
    1.39
    fluid
    1.39
    Activations Density 0.011%

    No Known Activations