© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 29608
    Prev
    Next
    INDEX
    Explanations

    the repeated phrase "as" used 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
    478
    +0.17
    0.9%
    502
    +0.14
    0.8%
    424
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.17
    0.17
    502
    +0.14
    0.15
    479
    +0.14
    0.15
    Negative Logits
    []
    -1.73
    ogether
    -1.51
    ritical
    -1.48
     together
    -1.47
    ATH
    -1.46
    ester
    -1.44
    ctors
    -1.43
    support
    -1.42
    therefore
    -1.40
    itness
    -1.39
    POSITIVE LOGITS
    ¶
    2.39
    ¾
    2.39
    °
    2.38
    ylum
    2.37
    phalt
    2.34
    ĨĴ
    2.31
    ·¸
    2.31
    ¹
    2.27
    Ĥ
    2.27
    µ
    2.24
    Activations Density 1.811%

    No Known Activations