Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27444
    Prev
    Next
    INDEX
    Explanations

    expressions of optimism or future expectations

    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
    376
    +0.24
    1.4%
    23
    +0.16
    0.9%
    156
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.24
    0.02
    74
    +0.16
    0.02
    250
    +0.15
    0.01
    Negative Logits
     alike
    -1.97
    §
    -1.85
    ĥ½
    -1.76
    PI
    -1.70
    erman
    -1.68
    )\].
    -1.62
    ERN
    -1.56
    ser
    -1.54
    atz
    -1.51
    PF
    -1.50
    POSITIVE LOGITS
     DAMAGE
    1.53
     Mn
    1.49
     Britain
    1.42
    yel
    1.38
     Void
    1.35
    balance
    1.34
    ghan
    1.33
     Unicode
    1.31
    bold
    1.29
     result
    1.27
    Activations Density 0.014%

    No Known Activations