© 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 EvalsExportsAPI 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. 29327
    Prev
    Next
    INDEX
    Explanations

    the term "span" 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
    376
    +0.15
    0.9%
    115
    +0.14
    0.8%
    298
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.15
    0.01
    138
    +0.14
    0.01
    135
    +0.14
    0.01
    Negative Logits
    ĥ
    -1.80
    ¯
    -1.79
    ¨
    -1.71
    Ĥ
    -1.65
    )$)
    -1.58
     peroxide
    -1.49
    ¦
    -1.49
     resultant
    -1.48
    rapeutic
    -1.48
    unnumbered
    -1.48
    POSITIVE LOGITS
    itars
    1.76
    iei
    1.69
    azi
    1.68
    ière
    1.68
    ões
    1.68
    iter
    1.67
    stones
    1.64
    iles
    1.61
    ies
    1.61
    obox
    1.60
    Activations Density 0.021%

    No Known Activations