© 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. 25948
    Prev
    Next
    INDEX
    Explanations

    phrases or terms that indicate significant health-related risks or conditions

    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
    80
    +0.12
    0.7%
    55
    +0.12
    0.7%
    12
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.04
    67
    +0.12
    0.03
    187
    +0.11
    0.03
    Negative Logits
    ixel
    -1.60
    à±ģ
    -1.53
    yscall
    -1.49
    blogger
    -1.48
    ↵	↵
    -1.48
     descendants
    -1.48
    amble
    -1.47
    formance
    -1.41
    nikov
    -1.39
    "}](#
    -1.39
    POSITIVE LOGITS
    ł
    1.63
    vere
    1.61
     pleasure
    1.53
    +)
    1.53
    tons
    1.39
     victory
    1.36
    uously
    1.35
    Ł
    1.34
    Ļ
    1.33
    mn
    1.33
    Activations Density 0.050%

    No Known Activations