© 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. 26863
    Prev
    Next
    INDEX
    Explanations

    commands or phrases emphasizing the importance of giving or providing assistance

    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
    91
    +0.12
    0.6%
    264
    +0.11
    0.6%
    488
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.38
    434
    +0.11
    0.30
    151
    +0.10
    0.30
    Negative Logits
    IRS
    -1.80
    ees
    -1.78
    phrine
    -1.68
    ICU
    -1.67
    UTH
    -1.63
    bigr
    -1.60
    ATH
    -1.56
    ringes
    -1.53
    ancock
    -1.52
     hours
    -1.52
    POSITIVE LOGITS
     ineffective
    1.52
     sanity
    1.44
     unsuccessful
    1.42
     grub
    1.36
     unpublished
    1.35
     exploited
    1.33
     crucial
    1.29
     exemplified
    1.28
     harmless
    1.27
     illustrative
    1.26
    Activations Density 1.669%

    No Known Activations