© 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. 27967
    Prev
    Next
    INDEX
    Explanations

    references to significant occurrences or happenings

    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
    16
    +0.13
    0.7%
    414
    +0.12
    0.7%
    336
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.13
    0.02
    110
    +0.12
    0.02
    223
    +0.11
    0.02
    Negative Logits
    ozyg
    -1.61
    dit
    -1.58
    oit
    -1.47
    anos
    -1.47
    oubt
    -1.46
    oes
    -1.42
    usion
    -1.41
    population
    -1.41
    utting
    -1.40
    lion
    -1.37
    POSITIVE LOGITS
    emic
    2.01
    IZE
    1.63
     inhibitors
    1.51
    Ļ
    1.47
     priority
    1.45
     inhibitor
    1.44
     prevention
    1.43
    ĨĴ
    1.40
    TRODUCTION
    1.39
     Threat
    1.38
    Activations Density 0.037%

    No Known Activations