Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27806
    Prev
    Next
    INDEX
    Explanations

    references to personal ownership or possession

    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
    +0.24
    1.3%
    394
    +0.13
    0.7%
    407
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.24
    0.03
    394
    +0.13
    0.03
    240
    +0.12
    0.03
    Negative Logits
    fer
    -1.60
    bred
    -1.47
    iast
    -1.47
    eder
    -1.43
    icity
    -1.37
     await
    -1.34
    activity
    -1.33
    ferr
    -1.32
    reporting
    -1.30
    ared
    -1.30
    POSITIVE LOGITS
    Īĺ
    2.88
    ĸ´
    2.87
    Ĥ¬
    2.85
    ĩ
    2.84
    ª
    2.80
    £
    2.70
    ·¸
    2.68
    Ļ
    2.63
    ĺ
    2.62
    ĥ
    2.62
    Activations Density 0.124%

    No Known Activations