© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 25715
    Prev
    Next
    INDEX
    Explanations

    questions that end with a question mark

    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
    115
    +0.17
    1.0%
    478
    +0.12
    0.6%
    27
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.17
    0.04
    133
    +0.12
    0.04
    505
    +0.11
    0.03
    Negative Logits
    "}](#
    -1.73
    pad
    -1.59
     thereof
    -1.55
    .](
    -1.52
    unit
    -1.48
    burst
    -1.47
    pez
    -1.46
    haus
    -1.43
     herein
    -1.42
     presented
    -1.40
    POSITIVE LOGITS
    Į
    2.87
    ĻĤ
    2.84
    ľĵ
    2.79
    §
    2.70
    ĥ½
    2.69
    ¤
    2.65
    ĵ
    2.60
    Ļª
    2.55
    ¨
    2.49
    ¼
    2.45
    Activations Density 1.573%

    No Known Activations