© 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. 30806
    Prev
    Next
    INDEX
    Explanations

    occurrences of the NSString data type in programming contexts

    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
    376
    +0.11
    0.6%
    306
    +0.11
    0.6%
    155
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.01
    57
    +0.11
    0.01
    385
    +0.10
    0.01
    Negative Logits
     done
    -1.55
    itors
    -1.44
     transgender
    -1.42
    herent
    -1.42
     scheduled
    -1.42
     happening
    -1.41
    ity
    -1.39
     already
    -1.38
    ductor
    -1.38
    wards
    -1.37
    POSITIVE LOGITS
    £
    2.20
    ģ
    1.94
    ª
    1.91
    ¡
    1.90
    Ļ
    1.83
    ¾
    1.83
    Ł
    1.77
    Ĵ
    1.75
    ungen
    1.71
    ¯
    1.70
    Activations Density 0.054%

    No Known Activations