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. 27376
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intention or purpose

    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
    388
    +0.13
    0.7%
    352
    +0.13
    0.7%
    22
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.38
    151
    +0.13
    0.31
    434
    +0.12
    0.30
    Negative Logits
    ankton
    -1.76
    ively
    -1.73
    aped
    -1.69
    apes
    -1.58
    elves
    -1.58
    yset
    -1.56
    efs
    -1.54
    erville
    -1.53
    tawa
    -1.52
    ky
    -1.51
    POSITIVE LOGITS
     cost
    1.54
     @
    1.52
     $$
    1.49
     [$\
    1.46
     ++
    1.44
     constraints
    1.42
     frame
    1.41
     frag
    1.40
     [$
    1.40
     break
    1.40
    Activations Density 1.625%

    No Known Activations