© 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. 24247
    Prev
    Next
    INDEX
    Explanations

    references to academic papers and their citation details

    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
    156
    +0.14
    0.8%
    352
    +0.13
    0.7%
    149
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.14
    0.04
    207
    +0.13
    0.05
    400
    +0.13
    0.04
    Negative Logits
    ¢
    -2.90
    ij
    -2.71
    º
    -2.69
    Ń
    -2.68
    §
    -2.65
    İ
    -2.65
    ·
    -2.65
    ¾
    -2.64
    Į
    -2.60
    £
    -2.54
    POSITIVE LOGITS
    INGTON
    1.66
     Synd
    1.57
    BY
    1.53
     Bundle
    1.44
     downs
    1.43
    ruption
    1.38
     ransom
    1.35
    seys
    1.33
    xico
    1.31
    innati
    1.29
    Activations Density 0.646%

    No Known Activations