© 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. 25326
    Prev
    Next
    INDEX
    Explanations

    indications of legal or judicial processes

    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
    326
    +0.14
    0.8%
    82
    +0.11
    0.6%
    102
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.14
    0.38
    53
    +0.11
    0.41
    56
    +0.10
    0.10
    Negative Logits
    unnumbered
    -1.57
    jsfiddle
    -1.28
    aret
    -1.28
    oulder
    -1.26
    ¼
    -1.26
     Movement
    -1.26
    )?
    -1.25
     Sure
    -1.24
    band
    -1.21
     means
    -1.20
    POSITIVE LOGITS
    mys
    1.55
    ian
    1.52
    azzo
    1.50
    ignon
    1.49
    icile
    1.49
    semin
    1.48
    gus
    1.47
    mente
    1.46
    ielle
    1.45
    imuth
    1.42
    Activations Density 4.901%

    No Known Activations