© 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. 29579
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Something" that indicate important or noteworthy items

    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
    +0.15
    0.8%
    40
    +0.13
    0.7%
    44
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.15
    0.01
    249
    +0.13
    0.01
    508
    +0.12
    0.01
    Negative Logits
    existence
    -1.60
    Property
    -1.49
    Case
    -1.48
    property
    -1.45
    unnumbered
    -1.43
    forcing
    -1.41
    Contents
    -1.40
    theless
    -1.39
    scribed
    -1.38
    awt
    -1.38
    POSITIVE LOGITS
    ¿½
    2.26
    «
    1.87
    Īĺ
    1.73
    anium
    1.68
    zol
    1.58
    ĻĤ
    1.53
     experiment
    1.42
    °
    1.41
     termed
    1.38
    ania
    1.37
    Activations Density 0.054%

    No Known Activations