© 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. 30768
    Prev
    Next
    INDEX
    Explanations

    repeated numeric values

    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
    362
    +0.19
    1.1%
    106
    +0.13
    0.8%
    458
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.19
    0.02
    106
    +0.13
    0.02
    307
    +0.13
    0.02
    Negative Logits
    hentication
    -1.78
    ureus
    -1.59
     least
    -1.54
    uppose
    -1.53
     paste
    -1.50
    ributors
    -1.49
     testify
    -1.46
     age
    -1.44
     Copyright
    -1.41
    opic
    -1.38
    POSITIVE LOGITS
    ®
    3.03
    ¶
    2.58
    ¾
    2.56
    µ
    2.44
    ¬
    2.33
    °
    2.31
    ²
    2.27
    ļ
    2.10
    ¥
    2.09
    ĥ½
    2.08
    Activations Density 0.034%

    No Known Activations