© 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. 30229
    Prev
    Next
    INDEX
    Explanations

    occurrences of "etc." indicating additional unspecified items or examples

    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
    256
    +0.14
    0.8%
    474
    +0.11
    0.6%
    83
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    256
    +0.14
    0.04
    83
    +0.11
    0.04
    25
    +0.11
    0.03
    Negative Logits
    ·¸
    -2.28
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.86
    <|outofrange|>
    -1.77
    ↵
    -1.77
    č↵
    -1.77
    č↵
    -1.77
    -1.77
    ↵↵
    -1.77
    ↵            ↵
    -1.77
    <|outofrange|>
    -1.77
    POSITIVE LOGITS
    arser
    1.60
    URI
    1.54
    iances
    1.53
    urai
    1.49
    usive
    1.48
    aurus
    1.41
    fy
    1.36
    ender
    1.34
    .),
    1.33
    .);
    1.32
    Activations Density 0.062%

    No Known Activations