© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26464
    Prev
    Next
    INDEX
    Explanations

    punctuation and its usage in context

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    89
    +0.11
    0.6%
    74
    +0.10
    0.6%
    131
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.11
    0.10
    499
    +0.10
    0.06
    422
    +0.10
    0.06
    Negative Logits
    documentclass
    -2.00
    abouts
    -1.68
     Congress
    -1.53
     ^[@
    -1.47
     _
    -1.44
    zig
    -1.38
    SH
    -1.37
    oval
    -1.35
    ging
    -1.34
    red
    -1.30
    POSITIVE LOGITS
    ÃŃf
    1.80
    cco
    1.77
    aceut
    1.74
    nier
    1.68
    inux
    1.68
    heets
    1.57
     Rptr
    1.55
    usiness
    1.49
    wegian
    1.48
     aussi
    1.43
    Activations Density 0.958%

    No Known Activations