© 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. 29050
    Prev
    Next
    INDEX
    Explanations

    references to award-winning works or achievements

    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
    156
    +0.19
    1.1%
    282
    +0.13
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    110
    +0.19
    0.01
    102
    +0.13
    0.01
    186
    +0.12
    0.01
    Negative Logits
    edu
    -1.61
    study
    -1.51
     Improvement
    -1.41
     Education
    -1.38
     cref
    -1.36
    reditation
    -1.36
    adem
    -1.35
     EPA
    -1.34
    ischer
    -1.33
    =======================
    -1.33
    POSITIVE LOGITS
    ĻĤ
    2.79
    ¯
    2.60
    ¸
    2.39
    Ģ
    2.31
    ¼
    2.09
    µ
    2.09
    Ħ
    1.97
    ³
    1.96
    ĩ
    1.92
    ł
    1.91
    Activations Density 2.939%

    No Known Activations