© 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. 2-MLP-SM
    11. 23261
    Prev
    Next
    INDEX
    Explanations

    various punctuation marks, particularly question marks and exclamation points

    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
    98
    +0.17
    0.9%
    235
    +0.16
    0.9%
    117
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.17
    0.07
    208
    +0.16
    0.04
    110
    +0.14
    0.04
    Negative Logits
    ĻĤ
    -2.38
    Ĭ
    -2.27
    ģ
    -2.20
    º
    -2.19
    ¿½
    -2.19
    Ĺ
    -2.18
    ħ
    -2.11
    ±
    -2.03
    ŀ
    -2.02
    ©
    -2.02
    POSITIVE LOGITS
    Submitted
    1.69
     based
    1.68
    Argued
    1.67
     \[[@
    1.66
     ([
    1.65
     Respondents
    1.60
    .^[@
    1.60
     located
    1.57
     borne
    1.54
    based
    1.54
    Activations Density 0.473%

    No Known Activations