© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26498
    Prev
    Next
    INDEX
    Explanations

    instances of the word "even"

    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
    225
    +0.17
    1.0%
    348
    +0.11
    0.6%
    13
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.17
    0.06
    250
    +0.11
    0.04
    230
    +0.10
    0.01
    Negative Logits
    coming
    -1.56
    utenant
    -1.48
    blocking
    -1.46
    verb
    -1.38
    ky
    -1.36
    tek
    -1.35
    ynaptic
    -1.34
    side
    -1.34
     investigating
    -1.32
     upside
    -1.31
    POSITIVE LOGITS
    ı
    4.24
    º
    4.24
    Ĩ
    4.20
    Į
    4.15
    İ
    4.13
    Ŀ
    4.10
    ij
    4.09
    ¬
    4.01
    »¿
    3.95
    ¾
    3.93
    Activations Density 0.159%

    No Known Activations