© 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. 29829
    Prev
    Next
    INDEX
    Explanations

    instances of non-English characters or symbols

    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
    443
    +0.13
    0.7%
    119
    +0.12
    0.7%
    373
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.04
    373
    +0.12
    0.04
    53
    +0.11
    0.04
    Negative Logits
     wide
    -1.51
     taken
    -1.47
     specificity
    -1.47
     find
    -1.46
     develop
    -1.46
     pause
    -1.44
     conclude
    -1.44
     specific
    -1.44
     broad
    -1.41
     Defendant
    -1.41
    POSITIVE LOGITS
    YPT
    1.85
    ÃŃf
    1.73
    vier
    1.69
    ionale
    1.67
    ixon
    1.58
    lei
    1.57
    aeda
    1.57
    idenote
    1.54
    stanbul
    1.53
    journals
    1.53
    Activations Density 5.035%

    No Known Activations