© 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. 25950
    Prev
    Next
    INDEX
    Explanations

    recurring patterns or structures in programming and error handling

    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
    465
    +0.14
    0.8%
    260
    +0.13
    0.7%
    230
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    448
    +0.14
    0.16
    316
    +0.13
    0.13
    124
    +0.13
    0.14
    Negative Logits
    ĨĴ
    -4.10
    ĸ´
    -3.89
    Ĩ
    -3.74
    ¦
    -3.67
    ¿
    -3.65
    Ĥ¬
    -3.60
    ¾
    -3.56
    Ń
    -3.51
    ¶
    -3.50
    §
    -3.48
    POSITIVE LOGITS
    unnumbered
    1.67
     spanning
    1.46
    imon
    1.40
     stop
    1.39
    ball
    1.39
    pub
    1.39
     space
    1.39
     ample
    1.37
     millenn
    1.36
    brid
    1.35
    Activations Density 0.886%

    No Known Activations