© 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. 0-MLP-SM
    11. 27184
    Prev
    Next
    INDEX
    Explanations

    instances of the word "dominant" and its variations in text

    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
    +0.28
    1.6%
    376
    +0.15
    0.9%
    159
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.28
    0.02
    487
    +0.15
    0.01
    30
    +0.13
    0.01
    Negative Logits
     Gates
    -1.51
    avir
    -1.40
    anson
    -1.39
    že
    -1.35
     trailing
    -1.33
    FFIR
    -1.32
     Month
    -1.31
    obbsee
    -1.29
    ARS
    -1.28
    GB
    -1.27
    POSITIVE LOGITS
    ¼
    2.93
    Ĭ
    2.67
    Ģ
    2.65
    Ļª
    2.54
    °
    2.52
    ļ
    2.50
    ĥ
    2.41
    µ
    2.38
    ¹
    2.31
    ģ
    2.31
    Activations Density 0.017%

    No Known Activations