© 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. 28565
    Prev
    Next
    INDEX
    Explanations

    patterns in structured data or markup formats

    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
    71
    +0.14
    0.8%
    111
    +0.13
    0.7%
    182
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.01
    40
    +0.13
    0.01
    175
    +0.13
    0.01
    Negative Logits
    ³
    -1.81
    ľ
    -1.75
    rier
    -1.67
    ides
    -1.62
    pper
    -1.54
    inating
    -1.50
    ipping
    -1.50
    upon
    -1.49
    ĩ
    -1.47
    zzo
    -1.46
    POSITIVE LOGITS
    krit
    1.84
    ULAR
    1.78
    smallcaps
    1.62
    CoV
    1.62
    izumab
    1.51
    statement
    1.51
    fony
    1.47
    skins
    1.45
    nement
    1.44
    lor
    1.43
    Activations Density 0.458%

    No Known Activations