© 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. 28478
    Prev
    Next
    INDEX
    Explanations

    instances of the word "focused."

    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
    +0.19
    1.1%
    156
    +0.16
    0.9%
    142
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.19
    0.02
    127
    +0.16
    0.01
    380
    +0.13
    0.01
    Negative Logits
    ħ
    -2.21
    Ī
    -2.09
    Ħ
    -1.94
    ŀ
    -1.91
    ½
    -1.90
    ĭ
    -1.89
    §
    -1.82
    ĨĴ
    -1.81
    ĥ
    -1.74
    ĥ½
    -1.72
    POSITIVE LOGITS
    line
    1.66
    ités
    1.55
    rangle
    1.52
    upt
    1.51
    acting
    1.51
    oon
    1.50
     Parenthood
    1.48
    lines
    1.46
    ISPR
    1.45
    erad
    1.38
    Activations Density 0.049%

    No Known Activations