© 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. 27177
    Prev
    Next
    INDEX
    Explanations

    references to a "Center" in various 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
    376
    +0.15
    0.8%
    156
    +0.14
    0.8%
    193
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.15
    0.01
    451
    +0.14
    0.01
    385
    +0.13
    0.01
    Negative Logits
    ¦
    -3.37
    §
    -3.24
    Ĥ
    -3.19
    ĥ½
    -3.08
    Ĥ¬
    -3.07
    ĥ
    -2.98
    ¯
    -2.97
    ¬
    -2.86
    ľ
    -2.82
    ·¸
    -2.77
    POSITIVE LOGITS
    piece
    2.14
    holder
    2.03
    yard
    2.02
    kot
    1.90
    pieces
    1.89
    àµį
    1.78
    kok
    1.77
    ière
    1.76
    ville
    1.72
    yards
    1.67
    Activations Density 0.008%

    No Known Activations