© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27901
    Prev
    Next
    INDEX
    Explanations

    expressions of high approval or positivity

    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
    199
    +0.15
    0.8%
    355
    +0.12
    0.6%
    260
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    199
    +0.15
    0.08
    355
    +0.12
    0.06
    346
    +0.12
    0.05
    Negative Logits
    uelle
    -1.68
    UAL
    -1.58
    camera
    -1.54
    otto
    -1.54
    isher
    -1.53
    rian
    -1.49
    ylene
    -1.48
    ABLE
    -1.48
    ardo
    -1.48
    ostat
    -1.46
    POSITIVE LOGITS
     contributions
    1.76
    ifies
    1.69
    ifiable
    1.69
     qualities
    1.59
     avail
    1.58
     friendships
    1.57
     arms
    1.55
     deeds
    1.54
     proportions
    1.54
     dividends
    1.53
    Activations Density 1.780%

    No Known Activations