© 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. 27173
    Prev
    Next
    INDEX
    Explanations

    the name "Serge."

    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
    376
    +0.13
    0.7%
    304
    +0.12
    0.7%
    357
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.13
    0.01
    357
    +0.12
    0.01
    71
    +0.12
    0.01
    Negative Logits
     sudden
    -1.79
     unusual
    -1.57
     late
    -1.56
     disastrous
    -1.49
     unprecedented
    -1.46
     different
    -1.45
     unexpected
    -1.42
     strange
    -1.42
    lying
    -1.42
     present
    -1.42
    POSITIVE LOGITS
    ¨
    2.36
    «
    2.07
    ¡
    1.96
    opan
    1.95
    atype
    1.95
    uelle
    1.90
    ī
    1.85
    ª
    1.83
    ģ
    1.83
    £
    1.80
    Activations Density 0.011%

    No Known Activations