© 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. 30443
    Prev
    Next
    INDEX
    Explanations

    reflections on personal experiences and self-identity

    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
    376
    +0.16
    0.9%
    353
    +0.14
    0.8%
    365
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.16
    0.04
    363
    +0.14
    0.02
    326
    +0.13
    0.02
    Negative Logits
    backs
    -1.55
    rap
    -1.50
     itself
    -1.49
     irregular
    -1.45
     trend
    -1.44
     herself
    -1.40
    ige
    -1.35
     indeed
    -1.34
     fibrillation
    -1.34
     addict
    -1.33
    POSITIVE LOGITS
    xico
    1.83
    chitz
    1.81
    ucid
    1.61
    ilen
    1.55
    chs
    1.55
    cretion
    1.53
    isters
    1.50
    isdiction
    1.49
    stic
    1.47
    isms
    1.46
    Activations Density 6.694%

    No Known Activations