© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28291
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal ownership or individual experience

    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
    172
    +0.15
    0.8%
    469
    +0.12
    0.7%
    116
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.15
    0.48
    98
    +0.12
    0.20
    228
    +0.11
    0.32
    Negative Logits
    ĻĤ
    -1.98
    ¾
    -1.84
    Ķ
    -1.84
    ¹
    -1.71
    ·¸
    -1.67
    ĩ
    -1.67
     spores
    -1.65
    Ĥ
    -1.63
    Ĺ
    -1.62
    ³
    -1.61
    POSITIVE LOGITS
    estly
    1.64
    void
    1.63
    iza
    1.54
    imation
    1.54
    itum
    1.49
    mann
    1.48
    ely
    1.43
     function
    1.42
    idge
    1.42
    ]{};
    1.41
    Activations Density 3.108%

    No Known Activations