© 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. 23109
    Prev
    Next
    INDEX
    Explanations

    sections of text labeled as "Introduction" or similar headings

    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%
    200
    +0.11
    0.6%
    74
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.17
    0.01
    319
    +0.11
    0.01
    167
    +0.10
    0.01
    Negative Logits
    Ĺ
    -3.01
    £
    -2.81
    ¯
    -2.72
    Ļ
    -2.64
    »¿
    -2.56
    ¢
    -2.54
    ®
    -2.53
    ª
    -2.52
    ĨĴ
    -2.51
    «
    -2.45
    POSITIVE LOGITS
     expired
    1.52
     equals
    1.49
     hood
    1.43
    ards
    1.41
    gage
    1.41
    ffic
    1.36
     iss
    1.35
    rification
    1.34
     capital
    1.33
     cake
    1.32
    Activations Density 0.033%

    No Known Activations