© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25072
    Prev
    Next
    INDEX
    Explanations

    occurrences of the suffix 'ens.'

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    432
    +0.14
    0.8%
    206
    +0.12
    0.7%
    117
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.14
    0.03
    162
    +0.12
    0.05
    206
    +0.11
    0.01
    Negative Logits
    ↵
    -1.98
    ↵
    -1.98
              ↵
    -1.98
     ↵
    -1.98
    -1.98
    -1.98
    ↵↵
    -1.98
    ↵
    -1.98
    ↵
    -1.98
    č↵
    -1.98
    POSITIVE LOGITS
    enburg
    1.49
    iring
    1.46
    ))$,
    1.42
     straightforward
    1.39
    js
    1.37
    ker
    1.37
    being
    1.37
    "]
    1.33
     born
    1.32
    ).)
    1.31
    Activations Density 0.586%

    No Known Activations