© 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. 30113
    Prev
    Next
    INDEX
    Explanations

    the presence of repeated elements throughout a technical or programming context

    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
    275
    +0.12
    0.7%
    95
    +0.10
    0.5%
    404
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    248
    +0.12
    0.19
    10
    +0.10
    0.16
    480
    +0.10
    0.14
    Negative Logits
    °
    -3.80
    ¯
    -3.64
    Ķ
    -3.62
    ŀ
    -3.62
    ±
    -3.52
    Ĭ
    -3.50
    £
    -3.44
    ¢
    -3.42
    ·¸
    -3.40
    ²
    -3.40
    POSITIVE LOGITS
    veau
    1.61
    through
    1.55
    mouth
    1.55
     encountered
    1.53
    esian
    1.52
    facial
    1.50
    eu
    1.47
    ander
    1.45
    cke
    1.44
    while
    1.42
    Activations Density 0.481%

    No Known Activations