© 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. 25334
    Prev
    Next
    INDEX
    Explanations

    references to significant effects or consequences 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
    110
    +0.13
    0.8%
    221
    +0.13
    0.8%
    200
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.13
    0.03
    110
    +0.13
    0.03
    268
    +0.12
    0.03
    Negative Logits
    reland
    -1.79
    npmjs
    -1.65
     trust
    -1.59
    pherd
    -1.50
    llo
    -1.50
    rica
    -1.48
    christ
    -1.47
     Worth
    -1.44
    ALTH
    -1.41
    rium
    -1.40
    POSITIVE LOGITS
    hole
    1.80
     situations
    1.68
     vector
    1.66
    ument
    1.64
    ł
    1.63
    igraph
    1.61
    holes
    1.55
    over
    1.53
     periods
    1.53
     collectors
    1.51
    Activations Density 0.091%

    No Known Activations