© 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. 28642
    Prev
    Next
    INDEX
    Explanations

    instances of the word "customized."

    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
    156
    +0.26
    1.5%
    29
    +0.12
    0.7%
    194
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.26
    0.01
    340
    +0.12
    0.01
    29
    +0.11
    0.01
    Negative Logits
     chance
    -1.74
    iko
    -1.72
    croft
    -1.52
    ño
    -1.45
    aze
    -1.42
     attempt
    -1.42
    eks
    -1.41
    eva
    -1.41
    ocardi
    -1.38
     gond
    -1.36
    POSITIVE LOGITS
    ¡
    3.31
    µ
    3.27
    Ĭ
    3.25
    ²
    3.24
    ¸
    3.17
    ł
    3.11
    ķ
    3.08
    ¢
    3.03
    »¿
    3.02
    ½
    3.00
    Activations Density 0.155%

    No Known Activations