© 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. 2-MLP-SM
    11. 23235
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific experimentation and solutions

    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
    252
    +0.14
    0.8%
    23
    +0.13
    0.7%
    65
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.14
    0.03
    65
    +0.13
    0.05
    23
    +0.12
    0.03
    Negative Logits
    she
    -1.81
    vant
    -1.76
    break
    -1.64
    ^-
    -1.64
    »¿
    -1.61
    xe
    -1.57
    )\]
    -1.53
    ¼
    -1.50
    -
    -1.50
    lig
    -1.50
    POSITIVE LOGITS
     happ
    1.77
     birthday
    1.53
     courage
    1.47
     Kubernetes
    1.43
     persistence
    1.41
     Yahoo
    1.41
     00000000000000000000000000000000
    1.40
    áĢº
    1.40
     cardinality
    1.38
     Azure
    1.38
    Activations Density 0.531%

    No Known Activations