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. 27468
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Mass."

    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%
    410
    +0.13
    0.7%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.19
    0.02
    26
    +0.13
    0.02
    437
    +0.11
    0.01
    Negative Logits
    rian
    -1.63
    ĥ
    -1.60
     my
    -1.55
    ¸
    -1.54
    kers
    -1.52
     track
    -1.48
    ³
    -1.46
    İ
    -1.45
    tering
    -1.44
    ters
    -1.44
    POSITIVE LOGITS
    ARRAY
    1.97
    ive
    1.61
    achusetts
    1.59
    IVE
    1.59
    IL
    1.55
    ived
    1.53
    BITS
    1.50
    acre
    1.50
     spectrometry
    1.46
    field
    1.45
    Activations Density 0.010%

    No Known Activations