© 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. 2-MLP-SM
    11. 25174
    Prev
    Next
    INDEX
    Explanations

    features related to product quality and performance

    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
    55
    +0.12
    0.7%
    170
    +0.11
    0.6%
    397
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.12
    0.06
    410
    +0.11
    0.03
    434
    +0.11
    0.07
    Negative Logits
    iors
    -1.85
    rès
    -1.81
     themselves
    -1.51
     surfaces
    -1.49
     outwe
    -1.46
    igen
    -1.43
    IRE
    -1.43
     thereto
    -1.40
    ħ
    -1.39
    ibilities
    -1.37
    POSITIVE LOGITS
    fered
    1.45
    Total
    1.39
     actionable
    1.37
     honest
    1.36
     total
    1.33
     recurrence
    1.31
    xiety
    1.30
    asted
    1.29
    zero
    1.21
    total
    1.20
    Activations Density 1.334%

    No Known Activations