© 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. 30086
    Prev
    Next
    INDEX
    Explanations

    the imperative form of verbs

    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
    26
    +0.15
    0.8%
    478
    +0.13
    0.7%
    177
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    485
    +0.15
    0.12
    486
    +0.13
    0.11
    387
    +0.12
    0.10
    Negative Logits
    ĻĤ
    -2.65
    Ļª
    -2.17
    ´
    -2.14
    »¿
    -2.10
    ĥ½
    -2.04
    ij
    -1.98
    ²
    -1.94
    ·¸
    -1.93
    Ł
    -1.86
    Ĺ
    -1.81
    POSITIVE LOGITS
    ota
    1.62
    gery
    1.56
    oti
    1.52
    otta
    1.45
    áĢ¬
    1.45
     Lanc
    1.45
    chanical
    1.43
     HREF
    1.39
    arta
    1.39
    order
    1.38
    Activations Density 0.090%

    No Known Activations