© 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. 25791
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" indicating connections in lists or conjunctions

    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
    244
    +0.12
    0.6%
    12
    +0.11
    0.6%
    277
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.12
    0.45
    209
    +0.11
    0.29
    402
    +0.10
    0.26
    Negative Logits
     instance
    -1.55
    arman
    -1.52
    bourne
    -1.48
     example
    -1.45
    apest
    -1.45
    ylase
    -1.44
    ches
    -1.42
    thon
    -1.41
    nez
    -1.40
    ighters
    -1.39
    POSITIVE LOGITS
    ISPR
    1.77
    over
    1.70
    isible
    1.50
     Reports
    1.46
    Ĺ
    1.45
    ĥ½
    1.42
    ĸ
    1.42
     Reporting
    1.40
    ¿½
    1.39
    quette
    1.37
    Activations Density 1.566%

    No Known Activations