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. 27282
    Prev
    Next
    INDEX
    Explanations

    the term "ic," which appears to denote an attribute or specialized style, potentially in technical or scientific contexts

    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
    276
    +0.12
    0.7%
    468
    +0.12
    0.7%
    180
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.12
    0.04
    395
    +0.12
    0.04
    276
    +0.11
    0.04
    Negative Logits
     orderly
    -1.59
    ľ
    -1.42
    atement
    -1.41
    edy
    -1.39
     Appellants
    -1.38
    isance
    -1.37
    arin
    -1.35
    upon
    -1.35
    INION
    -1.34
    ©
    -1.34
    POSITIVE LOGITS
    ulated
    1.72
    works
    1.53
    lock
    1.53
    len
    1.51
    ulation
    1.49
    ium
    1.47
    ulate
    1.47
    lint
    1.47
    leep
    1.47
    ethe
    1.45
    Activations Density 1.031%

    No Known Activations