© 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 EvalsExportsAPI 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. 28370
    Prev
    Next
    INDEX
    Explanations

    instances of the NS object in the document

    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
    410
    +0.14
    0.8%
    247
    +0.12
    0.7%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.14
    0.02
    330
    +0.12
    0.02
    247
    +0.12
    0.02
    Negative Logits
    abouts
    -2.11
    duct
    -1.69
     grandchildren
    -1.65
    enza
    -1.65
    aging
    -1.58
    ência
    -1.54
    acia
    -1.53
    itoring
    -1.46
     _________________________________
    -1.42
    yo
    -1.40
    POSITIVE LOGITS
    ERC
    1.91
    ultan
    1.81
    ĺ
    1.71
    Ń
    1.70
    FW
    1.64
    IENT
    1.57
    £
    1.56
    iang
    1.55
    ĸ
    1.54
    ª
    1.54
    Activations Density 4.933%

    No Known Activations