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. 27272
    Prev
    Next
    INDEX
    Explanations

    parentheses in numerical or programming 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
    45
    +0.12
    0.7%
    257
    +0.12
    0.7%
    366
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    188
    +0.12
    0.24
    486
    +0.12
    0.16
    154
    +0.12
    0.14
    Negative Logits
    ↵³³
    -1.76
    áĢº
    -1.58
    glycer
    -1.52
    android
    -1.45
     matter
    -1.37
     reversible
    -1.35
    wordpress
    -1.32
     probative
    -1.28
     INDIRECT
    -1.27
    edom
    -1.26
    POSITIVE LOGITS
    ices
    1.97
    iles
    1.86
    isions
    1.84
    ibilities
    1.67
    igo
    1.65
    ile
    1.51
    Ns
    1.49
    igos
    1.48
    iances
    1.46
    Ĺ
    1.44
    Activations Density 0.408%

    No Known Activations