© 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. 25912
    Prev
    Next
    INDEX
    Explanations

    references to unspecified or ambiguous subjects

    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
    118
    +0.12
    0.7%
    249
    +0.11
    0.6%
    367
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    367
    +0.12
    0.08
    359
    +0.11
    0.07
    118
    +0.11
    0.07
    Negative Logits
    ibaba
    -1.68
    uca
    -1.56
    oco
    -1.55
    oflu
    -1.51
     rest
    -1.50
    "`
    -1.46
    osecond
    -1.45
    oya
    -1.43
    &#
    -1.43
    ameth
    -1.43
    POSITIVE LOGITS
     than
    2.37
     Than
    2.18
    Than
    2.01
    than
    1.98
    Īĺ
    1.90
    world
    1.76
    Ļ
    1.64
    ¶
    1.63
     mammals
    1.62
    1.61
    Activations Density 6.407%

    No Known Activations