© 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. 28712
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft Excel

    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
    454
    +0.11
    0.7%
    410
    +0.11
    0.6%
    71
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.11
    0.01
    225
    +0.11
    0.01
    71
    +0.10
    0.01
    Negative Logits
    ³
    -2.78
    Ļª
    -2.77
    ĥ½
    -2.34
    ·
    -2.29
    ·¸
    -2.22
    ¯
    -2.21
    ½
    -2.12
    ¼
    -2.08
    Ħ
    -2.08
    ij
    -2.07
    POSITIVE LOGITS
    iei
    2.02
    ente
    1.93
    ière
    1.92
    ious
    1.85
    erals
    1.85
    enza
    1.73
    zilla
    1.72
    processor
    1.70
    ,[
    1.70
    entes
    1.68
    Activations Density 0.022%

    No Known Activations