© 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. 27710
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and syntax errors

    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
    115
    +0.13
    0.7%
    71
    +0.12
    0.6%
    288
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.13
    0.01
    159
    +0.12
    0.01
    71
    +0.11
    0.01
    Negative Logits
    Ĭ
    -2.28
    ĺ
    -2.17
    «
    -2.14
    ij
    -2.09
    Ħ
    -2.08
    ¼
    -2.01
    ¿½
    -2.00
    į
    -1.97
    ī
    -1.94
    ¢
    -1.92
    POSITIVE LOGITS
    pora
    1.82
    pen
    1.55
    antine
    1.54
    fee
    1.54
    dorff
    1.51
    minster
    1.50
    cro
    1.49
    inical
    1.49
    geries
    1.49
    oon
    1.48
    Activations Density 0.020%

    No Known Activations