© 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. 28465
    Prev
    Next
    INDEX
    Explanations

    instances of the plus symbol

    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
    115
    +0.12
    0.6%
    478
    +0.10
    0.6%
    354
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.12
    0.04
    354
    +0.10
    0.04
    311
    +0.10
    0.04
    Negative Logits
     honored
    -1.61
    idase
    -1.58
     âĪĴ
    -1.46
     unsupported
    -1.41
     AUTHOR
    -1.38
    anic
    -1.35
     percol
    -1.34
     holder
    -1.32
     gratefully
    -1.32
     ANN
    -1.31
    POSITIVE LOGITS
    Ĩ
    2.62
    ¸
    2.58
    ĨĴ
    2.58
    ³
    2.44
    ĥ½
    2.44
    ¶
    2.42
    Ĭ
    2.40
    º
    2.37
    Ļª
    2.36
    č↵
    2.36
    Activations Density 0.053%

    No Known Activations