© 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. 25678
    Prev
    Next
    INDEX
    Explanations

    explicit mentions of sexual content or themes

    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
    196
    +0.12
    0.7%
    427
    +0.12
    0.7%
    366
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.12
    0.04
    437
    +0.12
    0.04
    187
    +0.12
    0.04
    Negative Logits
    atu
    -1.78
    seys
    -1.77
    hev
    -1.70
    ató
    -1.64
    itian
    -1.59
    acter
    -1.57
    iei
    -1.56
    lections
    -1.50
    lig
    -1.50
    ousand
    -1.49
    POSITIVE LOGITS
     transition
    1.66
     response
    1.59
    Ķ
    1.58
    ŀ
    1.52
     Lancaster
    1.52
     crack
    1.47
     reappe
    1.40
     effort
    1.35
     Background
    1.35
     memories
    1.35
    Activations Density 0.051%

    No Known Activations