© 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. 27760
    Prev
    Next
    INDEX
    Explanations

    the repeated occurrence of the number 112

    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
    369
    +0.17
    0.9%
    412
    +0.13
    0.8%
    307
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.17
    0.02
    445
    +0.13
    0.01
    44
    +0.12
    0.02
    Negative Logits
    chers
    -1.90
     fame
    -1.84
     mean
    -1.75
     whom
    -1.72
     priori
    -1.43
     significance
    -1.42
    acles
    -1.38
    rition
    -1.38
     novelist
    -1.35
    ributors
    -1.33
    POSITIVE LOGITS
    ¶
    1.99
    ¬
    1.87
    ³
    1.79
    ¹
    1.77
    º
    1.74
    ª
    1.72
    ®
    1.66
    hart
    1.63
    ´
    1.62
    ·
    1.61
    Activations Density 0.017%

    No Known Activations