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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 27477
    Prev
    Next
    INDEX
    Explanations

    delivery-related terms and conditions

    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
    369
    +0.19
    1.1%
    220
    +0.14
    0.8%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.19
    0.01
    111
    +0.14
    0.01
    403
    +0.12
    0.01
    Negative Logits
    cluding
    -1.79
    tern
    -1.70
    cha
    -1.62
    quired
    -1.60
    neut
    -1.56
    cludes
    -1.50
    iginally
    -1.47
     dependence
    -1.45
     full
    -1.40
     lifetime
    -1.39
    POSITIVE LOGITS
    leys
    1.94
    oque
    1.94
    etto
    1.90
    aire
    1.74
    ERTY
    1.68
    enez
    1.67
    esan
    1.66
    ek
    1.66
    uxe
    1.57
    inux
    1.56
    Activations Density 0.012%

    No Known Activations