© 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. 2-MLP-SM
    11. 25617
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to conditional or defining statements

    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
    216
    +0.12
    0.7%
    200
    +0.11
    0.6%
    61
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.12
    0.03
    92
    +0.11
    0.02
    56
    +0.10
    0.09
    Negative Logits
     monopoly
    -1.68
     monopol
    -1.66
    usterity
    -1.62
    fall
    -1.59
     sovereignty
    -1.56
     ‘
    -1.56
     stolen
    -1.54
     vanished
    -1.51
    usions
    -1.49
     fortunes
    -1.49
    POSITIVE LOGITS
    ¡
    2.70
    ¬
    2.62
    °
    2.54
    ¦
    2.54
    ³
    2.41
    ¯
    2.32
    Ľ
    2.32
    ¸
    2.27
    µ
    2.20
    ª
    2.18
    Activations Density 1.730%

    No Known Activations