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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27784
    Prev
    Next
    INDEX
    Explanations

    references to the name "Martin."

    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
    +0.14
    0.8%
    184
    +0.13
    0.8%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.14
    0.01
    469
    +0.13
    0.01
    385
    +0.11
    0.01
    Negative Logits
    ĥ½
    -2.13
     '$
    -1.91
    ¬
    -1.83
    ?”
    -1.72
    ¿½
    -1.70
    Ģ
    -1.69
    ?_
    -1.62
     _________
    -1.61
    "?
    -1.61
    ?"
    -1.60
    POSITIVE LOGITS
    pora
    2.06
    cule
    1.96
    ique
    1.94
    cules
    1.79
    idone
    1.76
    dale
    1.74
    dorff
    1.74
    ico
    1.73
    boro
    1.71
    culo
    1.69
    Activations Density 0.016%

    No Known Activations