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. 27605
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stand."

    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
    380
    +0.14
    0.8%
    172
    +0.13
    0.7%
    111
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.14
    0.01
    172
    +0.13
    0.01
    381
    +0.13
    0.01
    Negative Logits
     vain
    -1.75
    CLAIM
    -1.74
    ·¸
    -1.66
     overtime
    -1.66
     MERCHANTABILITY
    -1.66
     expired
    -1.65
     disguise
    -1.60
    LLOW
    -1.59
     distress
    -1.55
     distressed
    -1.55
    POSITIVE LOGITS
    ards
    2.23
    finder
    2.00
    edly
    1.91
    ography
    1.84
    iative
    1.83
    iÄĩ
    1.83
    bench
    1.77
    ingly
    1.76
    ers
    1.76
    iom
    1.75
    Activations Density 0.007%

    No Known Activations