© 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. 23674
    Prev
    Next
    INDEX
    Explanations

    punctuation marks indicating the end of sentences

    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
    111
    +0.70
    8.1%
    156
    +0.58
    6.7%
    312
    +0.06
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.70
    0.36
    111
    +0.58
    0.35
    47
    +0.06
    0.35
    Negative Logits
    ¿½
    -2.67
    ²
    -2.67
    ij
    -2.57
    ħ
    -2.52
    Į
    -2.45
    ¦
    -2.44
    ĥ½
    -2.44
    ķ
    -2.42
    »
    -2.40
    ī
    -2.39
    POSITIVE LOGITS
     organizer
    1.18
     peers
    1.17
     fundament
    1.16
     este
    1.07
     contributor
    1.06
     lugar
    1.04
     Office
    1.03
     manager
    1.01
     intern
    1.01
     magazine
    1.00
    Activations Density 0.280%

    No Known Activations