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. 27289
    Prev
    Next
    INDEX
    Explanations

    the term "graft" in the context of medical procedures

    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
    360
    +0.12
    0.7%
    156
    +0.12
    0.7%
    189
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.12
    0.01
    189
    +0.12
    0.01
    360
    +0.11
    0.01
    Negative Logits
    ĥ½
    -1.87
    Į
    -1.83
    й
    -1.76
    zzo
    -1.75
    ?’
    -1.68
    lessly
    -1.63
    '));
    -1.59
    Č
    -1.55
    rie
    -1.54
    ¿
    -1.47
    POSITIVE LOGITS
    esan
    1.90
    erior
    1.89
    ivable
    1.77
    tube
    1.74
    "}](#
    1.67
    ceedings
    1.60
    culus
    1.58
    fecture
    1.58
    iative
    1.56
    actory
    1.53
    Activations Density 0.007%

    No Known Activations