© 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. 2-MLP-SM
    11. 24829
    Prev
    Next
    INDEX
    Explanations

    references to items or actions described with the indefinite article "a" and their modifiers

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    348
    +0.14
    0.7%
    464
    +0.12
    0.7%
    207
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.14
    0.06
    63
    +0.12
    0.07
    441
    +0.12
    0.04
    Negative Logits
     markup
    -1.54
     Oval
    -1.53
    soever
    -1.52
    hes
    -1.46
     kil
    -1.39
    irections
    -1.38
     contents
    -1.38
    cretion
    -1.36
     Photograph
    -1.35
    oor
    -1.32
    POSITIVE LOGITS
    ĨĴ
    3.37
    Īĺ
    3.21
    ı
    3.04
    Ń
    3.01
    ¿½
    2.95
    čč
    2.95
    ↵
    2.95
    ↵
    2.95
    <|outofrange|>
    2.95
    ↵
    2.95
    Activations Density 0.702%

    No Known Activations