© 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. 27164
    Prev
    Next
    INDEX
    Explanations

    mentions of user-related attributes or interactions in the text

    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
    156
    +0.18
    1.0%
    376
    +0.16
    1.0%
    193
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.18
    0.02
    357
    +0.16
    0.01
    34
    +0.12
    0.01
    Negative Logits
     why
    -2.22
    orms
    -1.83
     same
    -1.56
     nature
    -1.51
      ↵
    -1.49
    ]>
    -1.49
    nce
    -1.48
    amycin
    -1.47
     forth
    -1.46
    roller
    -1.45
    POSITIVE LOGITS
    ¾
    2.67
    »
    2.30
    ¼
    2.11
    ģ
    2.02
    ī
    1.98
    ¨
    1.96
    Īĺ
    1.91
    ist
    1.85
    ĸ´
    1.84
    istics
    1.79
    Activations Density 0.268%

    No Known Activations