© 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. 28876
    Prev
    Next
    INDEX
    Explanations

    instances of specific emotional expressions or sentiments

    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
    2
    +0.15
    0.9%
    111
    +0.14
    0.8%
    274
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    309
    +0.15
    0.02
    436
    +0.14
    0.02
    321
    +0.12
    0.02
    Negative Logits
     distance
    -1.58
     brightest
    -1.57
     shortest
    -1.55
    irement
    -1.54
     suppose
    -1.53
    abbit
    -1.51
     smallest
    -1.48
    onna
    -1.46
     Nile
    -1.45
     longest
    -1.42
    POSITIVE LOGITS
    enstein
    1.74
    sci
    1.69
    etts
    1.68
    arts
    1.67
    bie
    1.66
    ée
    1.65
    gren
    1.62
    ência
    1.61
    esan
    1.60
    caster
    1.57
    Activations Density 1.796%

    No Known Activations