© 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. 26335
    Prev
    Next
    INDEX
    Explanations

    the term "Array" within the context of programming or data structures

    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
    301
    +0.13
    0.8%
    391
    +0.12
    0.7%
    392
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.13
    0.02
    391
    +0.12
    0.02
    285
    +0.11
    0.02
    Negative Logits
    Ĥ
    -1.79
    }|^
    -1.68
    ³
    -1.67
    ij
    -1.64
     hereby
    -1.63
     suppose
    -1.62
    Ģ
    -1.59
    ¯
    -1.58
    rian
    -1.52
     user
    -1.52
    POSITIVE LOGITS
    pile
    1.93
    enstein
    1.86
    pora
    1.82
    cule
    1.80
    arian
    1.75
    borne
    1.75
    aggio
    1.71
    borg
    1.69
    iewicz
    1.67
    oque
    1.67
    Activations Density 0.014%

    No Known Activations