© 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. 28980
    Prev
    Next
    INDEX
    Explanations

    references to the Nobel Prize

    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
    22
    +0.13
    0.8%
    71
    +0.13
    0.7%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.13
    0.01
    159
    +0.13
    0.01
    111
    +0.12
    0.01
    Negative Logits
    aned
    -1.89
    aked
    -1.79
    hing
    -1.78
     its
    -1.77
    yet
    -1.63
     hers
    -1.63
    here
    -1.63
    hers
    -1.62
    yx
    -1.61
    forth
    -1.59
    POSITIVE LOGITS
    ĻĤ
    2.19
    ģ
    2.03
    ¼
    1.85
    "}](#
    1.84
    blems
    1.81
    »
    1.76
    ½
    1.65
     audience
    1.62
     Prize
    1.61
    \$
    1.59
    Activations Density 0.014%

    No Known Activations