© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27703
    Prev
    Next
    INDEX
    Explanations

    periods or other punctuation marks at the end of sentences

    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
    437
    +0.13
    0.7%
    435
    +0.12
    0.7%
    110
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.13
    0.08
    258
    +0.12
    0.07
    419
    +0.12
    0.06
    Negative Logits
    elves
    -1.75
    ality
    -1.56
    )](
    -1.54
    chool
    -1.53
    \]](
    -1.52
    moderate
    -1.48
    ffect
    -1.45
    eling
    -1.43
     -->
    -1.42
    woke
    -1.41
    POSITIVE LOGITS
    Ń
    4.07
    ¬
    3.71
    ↵
    3.46
    3.46
    3.46
     ↵
    3.46
    ↵
    3.46
    3.46
    3.46
    ↵
    3.46
    Activations Density 0.115%

    No Known Activations