© 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. 26195
    Prev
    Next
    INDEX
    Explanations

    terms related to aggregation in various 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
    156
    +0.17
    1.0%
    376
    +0.12
    0.7%
    90
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.17
    0.01
    272
    +0.12
    0.01
    449
    +0.11
    0.01
    Negative Logits
    }|^
    -1.85
     slightest
    -1.60
    asters
    -1.57
    >`
    -1.54
     somebody
    -1.52
    |^
    -1.52
     âĻª"
    -1.52
     someone
    -1.49
    )|^
    -1.48
    TRODUCTION
    -1.47
    POSITIVE LOGITS
    ļ
    2.14
    Ł
    2.01
    °
    1.96
    £
    1.90
     chambers
    1.80
     theory
    1.67
    ¡
    1.64
    ently
    1.64
    ŀ
    1.63
     positions
    1.63
    Activations Density 0.025%

    No Known Activations