© 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. 29615
    Prev
    Next
    INDEX
    Explanations

    mentions of minority groups or individuals

    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
    156
    +0.21
    1.2%
    376
    +0.14
    0.8%
    59
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.21
    0.01
    59
    +0.14
    0.01
    245
    +0.14
    0.02
    Negative Logits
    >';
    -1.58
    ável
    -1.38
     FIG
    -1.36
    rame
    -1.35
    mas
    -1.35
     jog
    -1.31
     Spacewatch
    -1.28
    ulpt
    -1.28
     bijection
    -1.23
     '.
    -1.22
    POSITIVE LOGITS
     quarters
    2.13
     areas
    1.63
    ī
    1.61
    ilities
    1.56
     lines
    1.53
    gered
    1.47
    ¦
    1.47
    ously
    1.45
     objections
    1.45
    {}{
    1.40
    Activations Density 0.021%

    No Known Activations