© 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. 0-MLP-SM
    11. 28978
    Prev
    Next
    INDEX
    Explanations

    expressions of emphasis or affirmation

    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
    304
    +0.12
    0.7%
    77
    +0.11
    0.6%
    171
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.12
    0.22
    185
    +0.11
    0.18
    165
    +0.10
    0.17
    Negative Logits
    ĥ
    -4.05
    ħ
    -3.91
    ↵
    -3.79
    č↵č↵
    -3.79
    <|outofrange|>
    -3.79
    <|outofrange|>
    -3.79
    -3.79
    -3.79
    ↵↵
    -3.79
         ↵
    -3.79
    POSITIVE LOGITS
    opause
    1.55
    ructure
    1.49
    aline
    1.48
    eration
    1.41
    onomy
    1.41
    riage
    1.38
     specifically
    1.37
     workforce
    1.36
    rogen
    1.36
    apter
    1.33
    Activations Density 0.395%

    No Known Activations