© 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. 30486
    Prev
    Next
    INDEX
    Explanations

    references to user interfaces in programming or software documentation

    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
    +0.26
    1.5%
    376
    +0.20
    1.2%
    413
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.26
    0.01
    320
    +0.20
    0.01
    416
    +0.12
    0.01
    Negative Logits
     why
    -1.52
     testament
    -1.49
     gay
    -1.48
     somebody
    -1.47
     anybody
    -1.42
    aying
    -1.41
     queer
    -1.37
     his
    -1.37
     trusted
    -1.37
     whom
    -1.36
    POSITIVE LOGITS
    icolor
    1.77
    ological
    1.62
    "}](#
    1.54
    ium
    1.54
    antine
    1.52
    wise
    1.51
    probe
    1.49
    heses
    1.46
    urious
    1.41
    elve
    1.39
    Activations Density 0.012%

    No Known Activations