© 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. 0-MLP-SM
    11. 26567
    Prev
    Next
    INDEX
    Explanations

    repeatedly used words that indicate relevance or importance

    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
    362
    +0.14
    0.8%
    110
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    265
    +0.14
    0.01
    344
    +0.12
    0.01
    110
    +0.11
    0.01
    Negative Logits
    enson
    -1.72
    smen
    -1.51
    ene
    -1.50
     Appeal
    -1.44
     Appeals
    -1.40
     Island
    -1.33
    ESH
    -1.31
     tam
    -1.30
     Die
    -1.28
     skate
    -1.27
    POSITIVE LOGITS
    ĻĤ
    2.88
    ľĵ
    1.86
    ³
    1.81
    £
    1.78
    º
    1.70
    ¢
    1.67
    ¡
    1.66
    ¬
    1.66
    ł
    1.59
    lies
    1.55
    Activations Density 4.695%

    No Known Activations