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. 27606
    Prev
    Next
    INDEX
    Explanations

    instances of the word "packed."

    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
    +0.19
    1.1%
    148
    +0.12
    0.7%
    305
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.19
    0.02
    255
    +0.12
    0.01
    305
    +0.12
    0.01
    Negative Logits
     Month
    -1.60
    ORS
    -1.60
     celebrated
    -1.58
     interested
    -1.55
    chers
    -1.54
     likely
    -1.54
     chance
    -1.52
     curious
    -1.50
    friends
    -1.49
    iginally
    -1.49
    POSITIVE LOGITS
    olini
    1.84
     offence
    1.73
    icture
    1.64
    ĻĤ
    1.62
    othal
    1.55
    oddsidemargin
    1.54
    stab
    1.53
    ulses
    1.49
    ounter
    1.48
    ussion
    1.47
    Activations Density 0.183%

    No Known Activations