© 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. 27676
    Prev
    Next
    INDEX
    Explanations

    instances of hypocrisy in various contexts

    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
    510
    +0.13
    0.8%
    468
    +0.13
    0.7%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.13
    0.01
    320
    +0.13
    0.01
    510
    +0.11
    0.01
    Negative Logits
    ı
    -2.94
    ·¸
    -2.82
    ¿½
    -2.77
    Ķ
    -2.74
    »
    -2.74
    Ĺ
    -2.57
    ¿
    -2.55
    Ļª
    -2.46
    ij
    -2.46
    ķ
    -2.35
    POSITIVE LOGITS
    enium
    1.85
    inates
    1.70
    unity
    1.59
    fors
    1.55
    erals
    1.54
    ató
    1.51
    ÃŃvel
    1.45
    bows
    1.44
    zilla
    1.44
    issance
    1.43
    Activations Density 0.003%

    No Known Activations