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

    Neuronpedia

    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. 0-MLP-SM
    11. 28330
    Prev
    Next
    INDEX
    Explanations

    instances of the word "evaluate" and its variations

    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
    +0.18
    1.1%
    156
    +0.15
    0.9%
    503
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    187
    +0.18
    0.01
    58
    +0.15
    0.01
    503
    +0.12
    0.01
    Negative Logits
     called
    -1.78
    called
    -1.75
     questioned
    -1.62
    itian
    -1.57
    rian
    -1.57
    #'
    -1.54
    })}
    -1.53
    ]);
    -1.53
    hip
    -1.51
    ']);
    -1.50
    POSITIVE LOGITS
    3.26
    ↵
    3.26
    ↵
    3.26
            ↵
    3.26
    <|outofrange|>
    3.26
    č↵
    3.26
    3.26
     ↵
    3.26
    3.26
    ↵↵
    3.26
    Activations Density 0.026%

    No Known Activations