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. 27355
    Prev
    Next
    INDEX
    Explanations

    the conditional word "if"

    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
    410
    +0.14
    0.8%
    268
    +0.12
    0.6%
    50
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.14
    0.11
    21
    +0.12
    0.07
    188
    +0.10
    0.07
    Negative Logits
    chester
    -1.72
     credibility
    -1.57
    idian
    -1.56
     deterg
    -1.50
     antigens
    -1.49
    >&
    -1.45
     vote
    -1.44
    ¿½
    -1.44
    erred
    -1.41
    atrix
    -1.40
    POSITIVE LOGITS
    simpl
    1.52
     Photograph
    1.51
    glass
    1.50
    leine
    1.49
    zes
    1.47
    shoot
    1.47
    own
    1.44
    example
    1.44
     objection
    1.42
    enÃŃ
    1.41
    Activations Density 3.696%

    No Known Activations