© 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. 2-MLP-SM
    11. 25897
    Prev
    Next
    INDEX
    Explanations

    references to death or fatality

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.16
    0.9%
    289
    +0.13
    0.7%
    373
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.16
    0.02
    94
    +0.13
    0.03
    249
    +0.13
    0.02
    Negative Logits
    Ļª
    -3.33
    Ħ
    -3.26
    ŀ
    -3.20
    ĺ
    -3.14
    ĨĴ
    -3.01
    £
    -3.00
    ¡
    -2.99
    IJ
    -2.88
    Ļ
    -2.85
    ij
    -2.82
    POSITIVE LOGITS
     herself
    1.84
     itself
    1.80
    iance
    1.79
    rops
    1.57
     wings
    1.52
    ments
    1.50
    ness
    1.48
     adm
    1.47
    ications
    1.45
    ives
    1.42
    Activations Density 0.229%

    No Known Activations