© 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. 26173
    Prev
    Next
    INDEX
    Explanations

    terms related to motivation and incentives

    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
    156
    +0.28
    1.6%
    23
    +0.20
    1.1%
    464
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.28
    0.02
    257
    +0.20
    0.02
    464
    +0.13
    0.02
    Negative Logits
    ĥ½
    -1.97
    ¾
    -1.84
    ħ
    -1.77
    ideo
    -1.71
    pread
    -1.70
    boro
    -1.70
    dorff
    -1.65
    igne
    -1.63
    pn
    -1.62
    imony
    -1.59
    POSITIVE LOGITS
     origin
    1.80
     default
    1.63
     error
    1.63
     underlying
    1.53
    ically
    1.49
     suppose
    1.47
     null
    1.41
     earliest
    1.40
    null
    1.40
     survive
    1.39
    Activations Density 0.078%

    No Known Activations