© 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. 2-MLP-SM
    11. 23002
    Prev
    Next
    INDEX
    Explanations

    references to research findings and results

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    293
    +0.13
    0.7%
    463
    +0.12
    0.7%
    34
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    277
    +0.13
    0.04
    394
    +0.12
    0.03
    335
    +0.11
    0.03
    Negative Logits
    Ŀ
    -2.41
    IJ
    -2.17
    Ĩ
    -2.15
    ı
    -2.04
    ¡
    -2.04
    ĸ
    -2.04
    Ļ
    -2.01
    Ł
    -2.00
    ħ
    -1.99
    ĨĴ
    -1.91
    POSITIVE LOGITS
    untime
    1.84
    case
    1.67
    chaft
    1.50
    tte
    1.48
    dup
    1.43
    ]_
    1.39
     du
    1.37
     puppet
    1.33
    susp
    1.30
    roup
    1.30
    Activations Density 0.257%

    No Known Activations