© 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. 29920
    Prev
    Next
    INDEX
    Explanations

    references to the year 1983

    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
    436
    +0.13
    0.7%
    322
    +0.13
    0.7%
    182
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    322
    +0.13
    0.01
    436
    +0.13
    0.01
    142
    +0.12
    0.01
    Negative Logits
    hab
    -1.63
    ights
    -1.58
    ]>
    -1.57
    ]]
    -1.55
    ...](
    -1.52
     behold
    -1.52
    ast
    -1.50
     bil
    -1.50
     dist
    -1.45
     whisk
    -1.45
    POSITIVE LOGITS
    ERT
    1.75
    ulent
    1.65
    msgstr
    1.62
    UNIT
    1.58
     000
    1.57
    igraph
    1.55
    UE
    1.54
    ellular
    1.53
    etable
    1.51
    inetics
    1.51
    Activations Density 0.026%

    No Known Activations