© 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. 29791
    Prev
    Next
    INDEX
    Explanations

    repeated symbols or patterns in 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
    478
    +0.16
    0.9%
    350
    +0.14
    0.8%
    487
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    273
    +0.16
    0.05
    42
    +0.14
    0.05
    487
    +0.13
    0.05
    Negative Logits
    anic
    -1.92
    asting
    -1.76
     **
    -1.69
    izing
    -1.69
    iser
    -1.65
    \*
    -1.61
    )](
    -1.53
     (\#
    -1.52
    .](
    -1.52
     ![](
    -1.49
    POSITIVE LOGITS
    ¼
    2.78
    ½
    2.61
    ¹
    2.46
    ·¸
    2.40
    ·
    2.27
    ĵ
    2.25
    ĥ½
    2.24
    ¸
    2.21
    º
    2.17
    ±
    2.16
    Activations Density 0.360%

    No Known Activations