© 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. 28537
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of specific phrases or terms

    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
    495
    +0.14
    0.8%
    21
    +0.14
    0.8%
    81
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    368
    +0.14
    0.12
    402
    +0.14
    0.12
    426
    +0.12
    0.10
    Negative Logits
    heit
    -1.68
    ween
    -1.60
    atta
    -1.51
    scale
    -1.51
    apon
    -1.46
    "}](#
    -1.46
     midst
    -1.42
    undry
    -1.41
    istration
    -1.40
    ternal
    -1.39
    POSITIVE LOGITS
    ´
    2.27
    ¿
    2.23
    ĺ
    2.23
    ĨĴ
    2.17
    ĩ
    2.17
    º
    2.16
    ©
    2.13
    ↵
    2.08
    ↵
    2.08
              ↵
    2.08
    Activations Density 0.635%

    No Known Activations