© 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. 28555
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "labeled" or its variations

    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
    376
    +0.20
    1.1%
    156
    +0.16
    0.9%
    2
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.20
    0.01
    470
    +0.16
    0.01
    167
    +0.16
    0.01
    Negative Logits
    IJ
    -2.42
    «
    -2.41
    ĭ
    -2.34
    ı
    -2.12
    »¿
    -2.10
    ĨĴ
    -2.10
    Ĺ
    -2.09
    Ĩ
    -2.02
    ±
    -1.95
    ħ
    -1.88
    POSITIVE LOGITS
     prints
    1.62
     wrong
    1.54
    gres
    1.51
    emeter
    1.50
    etect
    1.46
     kidding
    1.45
    emetery
    1.43
    ault
    1.40
     office
    1.39
    cif
    1.37
    Activations Density 0.008%

    No Known Activations